Computation and Language (cs.CL)

Abstract: Little attention has been paid on \underline{EA}rly \underline{R}umor \underline{D}etection (EARD), and EARD performance was evaluated inappropriately on a few datasets where the actual early-stage information is largely missing. To reverse such situation, we construct BEARD, a new \underline{B}enchmark dataset for \underline{EARD}, based on claims from fact-checking websites by trying to gather as many early relevant posts as possible. We also propose HEARD, a novel model based on neural \underline{H}awkes process for \underline{EARD}, which can guide a generic rumor detection model to make timely, accurate and stable predictions. Experiments show that HEARD achieves effective EARD performance on two commonly used general rumor detection datasets and our BEARD dataset.

Abstract: Colexification refers to the linguistic phenomenon where a single lexical form is used to convey multiple meanings. By studying cross-lingual colexifications, researchers have gained valuable insights into fields such as psycholinguistics and cognitive sciences [Jackson et al.,2019]. While several multilingual colexification datasets exist, there is untapped potential in using this information to bootstrap datasets across such semantic features. In this paper, we aim to demonstrate how colexifications can be leveraged to create such cross-lingual datasets. We showcase curation procedures which result in a dataset covering 142 languages across 21 language families across the world. The dataset includes ratings of concreteness and affectiveness, mapped with phonemes and phonological features. We further analyze the dataset along different dimensions to demonstrate potential of the proposed procedures in facilitating further interdisciplinary research in psychology, cognitive science, and multilingual natural language processing (NLP). Based on initial investigations, we observe that i) colexifications that are closer in concreteness/affectiveness are more likely to colexify; ii) certain initial/last phonemes are significantly correlated with concreteness/affectiveness intra language families, such as /k/ as the initial phoneme in both Turkic and Tai-Kadai correlated with concreteness, and /p/ in Dravidian and Sino-Tibetan correlated with Valence; iii) the type-to-token ratio (TTR) of phonemes are positively correlated with concreteness across several language families, while the length of phoneme segments are negatively correlated with concreteness; iv) certain phonological features are negatively correlated with concreteness across languages. The dataset is made public online for further research.

Abstract: Neural QCFG is a grammar-based sequence-tosequence (seq2seq) model with strong inductive biases on hierarchical structures. It excels in interpretability and generalization but suffers from expensive inference. In this paper, we study two low-rank variants of Neural QCFG for faster inference with different trade-offs between efficiency and expressiveness. Furthermore, utilizing the symbolic interface provided by the grammar, we introduce two soft constraints over tree hierarchy and source coverage. We experiment with various datasets and find that our models outperform vanilla Neural QCFG in most settings.

Abstract: In this paper, we present the ``joint pre-training and local re-training'' framework for learning and applying multi-source knowledge graph (KG) embeddings. We are motivated by the fact that different KGs contain complementary information to improve KG embeddings and downstream tasks. We pre-train a large teacher KG embedding model over linked multi-source KGs and distill knowledge to train a student model for a task-specific KG. To enable knowledge transfer across different KGs, we use entity alignment to build a linked subgraph for connecting the pre-trained KGs and the target KG. The linked subgraph is re-trained for three-level knowledge distillation from the teacher to the student, i.e., feature knowledge distillation, network knowledge distillation, and prediction knowledge distillation, to generate more expressive embeddings. The teacher model can be reused for different target KGs and tasks without having to train from scratch. We conduct extensive experiments to demonstrate the effectiveness and efficiency of our framework.

Abstract: Spoken languages often utilise intonation, rhythm, intensity, and structure, to communicate intention, which can be interpreted differently depending on the rhythm of speech of their utterance. These speech acts provide the foundation of communication and are unique in expression to the language. Recent advancements in attention-based models, demonstrating their ability to learn powerful representations from multilingual datasets, have performed well in speech tasks and are ideal to model specific tasks in low resource languages. Here, we develop a novel multimodal approach combining two models, wav2vec2.0 for audio and MarianMT for text translation, by using multimodal attention fusion to predict speech acts in our prepared Bengali speech corpus. We also show that our model BeAts ($\underline{\textbf{Be}}$ngali speech acts recognition using Multimodal $\underline{\textbf{At}}$tention Fu$\underline{\textbf{s}}$ion) significantly outperforms both the unimodal baseline using only speech data and a simpler bimodal fusion using both speech and text data. Project page: https://soumitri2001.github.io/BeAts

Abstract: Pronunciation assessment is a major challenge in the computer-aided pronunciation training system, especially at the word (phoneme)-level. To obtain word (phoneme)-level scores, current methods usually rely on aligning components to obtain acoustic features of each word (phoneme), which limits the performance of assessment to the accuracy of alignments. Therefore, to address this problem, we propose a simple yet effective method, namely \underline{M}asked pre-training for \underline{P}ronunciation \underline{A}ssessment (MPA). Specifically, by incorporating a mask-predict strategy, our MPA supports end-to-end training without leveraging any aligning components and can solve misalignment issues to a large extent during prediction. Furthermore, we design two evaluation strategies to enable our model to conduct assessments in both unsupervised and supervised settings. Experimental results on SpeechOcean762 dataset demonstrate that MPA could achieve better performance than previous methods, without any explicit alignment. In spite of this, MPA still has some limitations, such as requiring more inference time and reference text. They expect to be addressed in future work.

Abstract: Utilizing language models (LMs) without internal access is becoming an attractive paradigm in the field of NLP as many cutting-edge LMs are released through APIs and boast a massive scale. The de-facto method in this type of black-box scenario is known as prompting, which has shown progressive performance enhancements in situations where data labels are scarce or unavailable. Despite their efficacy, they still fall short in comparison to fully supervised counterparts and are generally brittle to slight modifications. In this paper, we propose Clustering-enhanced Linear Discriminative Analysis, a novel approach that improves the text classification accuracy with a very weak-supervision signal (i.e., name of the labels). Our framework draws a precise decision boundary without accessing weights or gradients of the LM model or data labels. The core ideas of CELDA are twofold: (1) extracting a refined pseudo-labeled dataset from an unlabeled dataset, and (2) training a lightweight and robust model on the top of LM, which learns an accurate decision boundary from an extracted noisy dataset. Throughout in-depth investigations on various datasets, we demonstrated that CELDA reaches new state-of-the-art in weakly-supervised text classification and narrows the gap with a fully-supervised model. Additionally, our proposed methodology can be applied universally to any LM and has the potential to scale to larger models, making it a more viable option for utilizing large LMs.

Abstract: Recent research has focused on enhancing the capability of smaller models through imitation learning, drawing on the outputs generated by large foundation models (LFMs). A number of issues impact the quality of these models, ranging from limited imitation signals from shallow LFM outputs; small scale homogeneous training data; and most notably a lack of rigorous evaluation resulting in overestimating the small model's capability as they tend to learn to imitate the style, but not the reasoning process of LFMs. To address these challenges, we develop Orca (We are working with our legal team to publicly release a diff of the model weights in accordance with LLaMA's release policy to be published at https://aka.ms/orca-lm), a 13-billion parameter model that learns to imitate the reasoning process of LFMs. Orca learns from rich signals from GPT-4 including explanation traces; step-by-step thought processes; and other complex instructions, guided by teacher assistance from ChatGPT. To promote this progressive learning, we tap into large-scale and diverse imitation data with judicious sampling and selection. Orca surpasses conventional state-of-the-art instruction-tuned models such as Vicuna-13B by more than 100% in complex zero-shot reasoning benchmarks like Big-Bench Hard (BBH) and 42% on AGIEval. Moreover, Orca reaches parity with ChatGPT on the BBH benchmark and shows competitive performance (4 pts gap with optimized system message) in professional and academic examinations like the SAT, LSAT, GRE, and GMAT, both in zero-shot settings without CoT; while trailing behind GPT-4. Our research indicates that learning from step-by-step explanations, whether these are generated by humans or more advanced AI models, is a promising direction to improve model capabilities and skills.

Abstract: The standard Gaussian Process (GP) only considers a single output sample per input in the training set. Datasets for subjective tasks, such as spoken language assessment, may be annotated with output labels from multiple human raters per input. This paper proposes to generalise the GP to allow for these multiple output samples in the training set, and thus make use of available output uncertainty information. This differs from a multi-output GP, as all output samples are from the same task here. The output density function is formulated to be the joint likelihood of observing all output samples, and latent variables are not repeated to reduce computation cost. The test set predictions are inferred similarly to a standard GP, with a difference being in the optimised hyper-parameters. This is evaluated on speechocean762, showing that it allows the GP to compute a test set output distribution that is more similar to the collection of reference outputs from the multiple human raters.

Abstract: Medical progress notes play a crucial role in documenting a patient's hospital journey, including his or her condition, treatment plan, and any updates for healthcare providers. Automatic summarisation of a patient's problems in the form of a problem list can aid stakeholders in understanding a patient's condition, reducing workload and cognitive bias. BioNLP 2023 Shared Task 1A focuses on generating a list of diagnoses and problems from the provider's progress notes during hospitalisation. In this paper, we introduce our proposed approach to this task, which integrates two complementary components. One component employs large language models (LLMs) for data augmentation; the other is an abstractive summarisation LLM with a novel pre-training objective for generating the patients' problems summarised as a list. Our approach was ranked second among all submissions to the shared task. The performance of our model on the development and test datasets shows that our approach is more robust on unknown data, with an improvement of up to 3.1 points over the same size of the larger model.

Abstract: Adapters have emerged as a modular and parameter-efficient approach to (zero-shot) cross-lingual transfer. The established MAD-X framework employs separate language and task adapters which can be arbitrarily combined to perform the transfer of any task to any target language. Subsequently, BAD-X, an extension of the MAD-X framework, achieves improved transfer at the cost of MAD-X's modularity by creating "bilingual" adapters specific to the source-target language pair. In this work, we aim to take the best of both worlds by (i) fine-tuning task adapters adapted to the target language(s) (so-called "target language-ready" (TLR) adapters) to maintain high transfer performance, but (ii) without sacrificing the highly modular design of MAD-X. The main idea of "target language-ready" adapters is to resolve the training-vs-inference discrepancy of MAD-X: the task adapter "sees" the target language adapter for the very first time during inference, and thus might not be fully compatible with it. We address this mismatch by exposing the task adapter to the target language adapter during training, and empirically validate several variants of the idea: in the simplest form, we alternate between using the source and target language adapters during task adapter training, which can be generalized to cycling over any set of language adapters. We evaluate different TLR-based transfer configurations with varying degrees of generality across a suite of standard cross-lingual benchmarks, and find that the most general (and thus most modular) configuration consistently outperforms MAD-X and BAD-X on most tasks and languages.

Abstract: Style is an important concept in today's challenges in natural language generating. After the success in the field of image style transfer, the task of text style transfer became actual and attractive. Researchers are also interested in the tasks of style reproducing in generation of the poetic text. Evaluation of style reproducing in natural poetry generation remains a problem. I used 3 character-based LSTM-models to work with style reproducing assessment. All three models were trained on the corpus of texts by famous Russian-speaking poets. Samples were shown to the assessors and 4 answer options were offered, the style of which poet this sample reproduces. In addition, the assessors were asked how well they were familiar with the work of the poet they had named. Students studying history of literature were the assessors, 94 answers were received. It has appeared that accuracy of definition of style increases if the assessor can quote the poet by heart. Each model showed at least 0.7 macro-average accuracy. The experiment showed that it is better to involve a professional rather than a naive reader in the evaluation of style in the tasks of poetry generation, while lstm models are good at reproducing the style of Russian poets even on a limited training corpus.

Abstract: This study aimed to develop an algorithm to automatically extract annotations for chest X-ray classification models from German thoracic radiology reports. An automatic label extraction model was designed based on the CheXpert architecture, and a web-based annotation interface was created for iterative improvements. Results showed that automated label extraction can reduce time spent on manual labeling and improve overall modeling performance. The model trained on automatically extracted labels performed competitively to manually labeled data and strongly outperformed the model trained on publicly available data.

Abstract: Without any explicit cross-lingual training data, multilingual language models can achieve cross-lingual transfer. One common way to improve this transfer is to perform realignment steps before fine-tuning, i.e., to train the model to build similar representations for pairs of words from translated sentences. But such realignment methods were found to not always improve results across languages and tasks, which raises the question of whether aligned representations are truly beneficial for cross-lingual transfer. We provide evidence that alignment is actually significantly correlated with cross-lingual transfer across languages, models and random seeds. We show that fine-tuning can have a significant impact on alignment, depending mainly on the downstream task and the model. Finally, we show that realignment can, in some instances, improve cross-lingual transfer, and we identify conditions in which realignment methods provide significant improvements. Namely, we find that realignment works better on tasks for which alignment is correlated with cross-lingual transfer when generalizing to a distant language and with smaller models, as well as when using a bilingual dictionary rather than FastAlign to extract realignment pairs. For example, for POS-tagging, between English and Arabic, realignment can bring a +15.8 accuracy improvement on distilmBERT, even outperforming XLM-R Large by 1.7. We thus advocate for further research on realignment methods for smaller multilingual models as an alternative to scaling.

Abstract: Text simplification aims to make the text easier to understand by applying rewriting transformations. There has been very little research on Chinese text simplification for a long time. The lack of generic evaluation data is an essential reason for this phenomenon. In this paper, we introduce MCTS, a multi-reference Chinese text simplification dataset. We describe the annotation process of the dataset and provide a detailed analysis of it. Furthermore, we evaluate the performance of some unsupervised methods and advanced large language models. We hope to build a basic understanding of Chinese text simplification through the foundational work and provide references for future research. We release our data at https://github.com/blcuicall/mcts.

Abstract: We model learning of abstract symbolic concepts by performing Bayesian inference over utterances in natural language. For efficient inference, we use a large language model as a proposal distribution. We fit a prior to human data to better model human learners, and evaluate on both generative and logical concepts.

Abstract: Natural language understanding (NLU) is an essential branch of natural language processing, which relies on representations generated by pre-trained language models (PLMs). However, PLMs primarily focus on acquiring lexico-semantic information, while they may be unable to adequately handle the meaning of constructions. To address this issue, we introduce construction grammar (CxG), which highlights the pairings of form and meaning, to enrich language representation. We adopt usage-based construction grammar as the basis of our work, which is highly compatible with statistical models such as PLMs. Then a HyCxG framework is proposed to enhance language representation through a three-stage solution. First, all constructions are extracted from sentences via a slot-constraints approach. As constructions can overlap with each other, bringing redundancy and imbalance, we formulate the conditional max coverage problem for selecting the discriminative constructions. Finally, we propose a relational hypergraph attention network to acquire representation from constructional information by capturing high-order word interactions among constructions. Extensive experiments demonstrate the superiority of the proposed model on a variety of NLU tasks.

Abstract: Verbal deception has been studied in psychology, forensics, and computational linguistics for a variety of reasons, like understanding behaviour patterns, identifying false testimonies, and detecting deception in online communication. Varying motivations across research fields lead to differences in the domain choices to study and in the conceptualization of deception, making it hard to compare models and build robust deception detection systems for a given language. With this paper, we improve this situation by surveying available English deception datasets which include domains like social media reviews, court testimonials, opinion statements on specific topics, and deceptive dialogues from online strategy games. We consolidate these datasets into a single unified corpus. Based on this resource, we conduct a correlation analysis of linguistic cues of deception across datasets to understand the differences and perform cross-corpus modeling experiments which show that a cross-domain generalization is challenging to achieve. The unified deception corpus (UNIDECOR) can be obtained from https://www.ims.uni-stuttgart.de/data/unidecor.

Abstract: Despite the rising prevalence of neural sequence models, recent empirical evidences suggest their deficiency in compositional generalization. One of the current de-facto solutions to this problem is compositional data augmentation, aiming to incur additional compositional inductive bias. Nonetheless, the improvement offered by existing handcrafted augmentation strategies is limited when successful systematic generalization of neural sequence models requires multi-grained compositional bias (i.e., not limited to either lexical or structural biases only) or differentiation of training sequences in an imbalanced difficulty distribution. To address the two challenges, we first propose a novel compositional augmentation strategy dubbed \textbf{Span} \textbf{Sub}stitution (SpanSub) that enables multi-grained composition of substantial substructures in the whole training set. Over and above that, we introduce the \textbf{L}earning \textbf{to} \textbf{S}ubstitute \textbf{S}pan (L2S2) framework which empowers the learning of span substitution probabilities in SpanSub in an end-to-end manner by maximizing the loss of neural sequence models, so as to outweigh those challenging compositions with elusive concepts and novel surroundings. Our empirical results on three standard compositional generalization benchmarks, including SCAN, COGS and GeoQuery (with an improvement of at most 66.5\%, 10.3\%, 1.2\%, respectively), demonstrate the superiority of SpanSub, %the learning framework L2S2 and their combination.

Abstract: Conversational recommender systems (CRSs) aim to provide recommendation services via natural language conversations. Although a number of approaches have been proposed for developing capable CRSs, they typically rely on sufficient training data for training. Since it is difficult to annotate recommendation-oriented dialogue datasets, existing CRS approaches often suffer from the issue of insufficient training due to the scarcity of training data. To address this issue, in this paper, we propose a CounterFactual data simulation approach for CRS, named CFCRS, to alleviate the issue of data scarcity in CRSs. Our approach is developed based on the framework of counterfactual data augmentation, which gradually incorporates the rewriting to the user preference from a real dialogue without interfering with the entire conversation flow. To develop our approach, we characterize user preference and organize the conversation flow by the entities involved in the dialogue, and design a multi-stage recommendation dialogue simulator based on a conversation flow language model. Under the guidance of the learned user preference and dialogue schema, the flow language model can produce reasonable, coherent conversation flows, which can be further realized into complete dialogues. Based on the simulator, we perform the intervention at the representations of the interacted entities of target users, and design an adversarial training method with a curriculum schedule that can gradually optimize the data augmentation strategy. Extensive experiments show that our approach can consistently boost the performance of several competitive CRSs, and outperform other data augmentation methods, especially when the training data is limited. Our code is publicly available at https://github.com/RUCAIBox/CFCRS.

Abstract: We present Video-LLaMA, a multi-modal framework that empowers Large Language Models (LLMs) with the capability of understanding both visual and auditory content in the video. Video-LLaMA bootstraps cross-modal training from the frozen pre-trained visual \& audio encoders and the frozen LLMs. Unlike previous vision- LLMs that focus on static image comprehensions such as MiniGPT-4~\citep{zhu2023minigpt} and LLaVA~\citep{liu2023visualit}, Video-LLaMA tackles two challenges in video understanding: (1) capturing the temporal changes in visual scenes, (2) integrating audio-visual signals. For the first challenge, we propose Video Q-former to extend the pre-trained image encoder to a video encoder and introduce a video-to-text generation task to learn video-language correspondence. For the second challenge, we leverage ImageBind~\citep{girdhar2023imagebind} as the pre-trained audio encoder which performs exceptionally well in aligning different modalities to a common embedding space. And then introduce an Audio Q-former to learn auditory query tokens. To align the output of both visual \& audio encoder with LLM's embedding space, we train Video-LLaMA on a large-scale vision caption dataset and a hign-quantity vision-instruction-tuning dataset. We found Video-LLaMA showcases the ability to perceive and comprehend video content, generating meaningful responses that are grounded in the visual and auditory information present in the videos. This highlights the potential of Video-LLaMA as a promising prototype for audio-visual AI assistants. Our code, pre-trained model, and demo are available at \url{https://github.com/DAMO-NLP-SG/Video-LLaMA}.

Abstract: This evidence-based position paper critiques current research practices within the language model pre-training literature. Despite rapid recent progress afforded by increasingly better pre-trained language models (PLMs), current PLM research practices often conflate different possible sources of model improvement, without conducting proper ablation studies and principled comparisons between different models under comparable conditions. These practices (i) leave us ill-equipped to understand which pre-training approaches should be used under what circumstances; (ii) impede reproducibility and credit assignment; and (iii) render it difficult to understand: "How exactly does each factor contribute to the progress that we have today?" We provide a case in point by revisiting the success of BERT over its baselines, ELMo and GPT-1, and demonstrate how -- under comparable conditions where the baselines are tuned to a similar extent -- these baselines (and even-simpler variants thereof) can, in fact, achieve competitive or better performance than BERT. These findings demonstrate how disentangling different factors of model improvements can lead to valuable new insights. We conclude with recommendations for how to encourage and incentivize this line of work, and accelerate progress towards a better and more systematic understanding of what factors drive the progress of our foundation models today.

Abstract: In contrast to large text corpora, knowledge graphs (KG) provide dense and structured representations of factual information. This makes them attractive for systems that supplement or ground the knowledge found in pre-trained language models with an external knowledge source. This has especially been the case for classification tasks, where recent work has focused on creating pipeline models that retrieve information from KGs like ConceptNet as additional context. Many of these models consist of multiple components, and although they differ in the number and nature of these parts, they all have in common that for some given text query, they attempt to identify and retrieve a relevant subgraph from the KG. Due to the noise and idiosyncrasies often found in KGs, it is not known how current methods compare to a scenario where the aligned subgraph is completely relevant to the query. In this work, we try to bridge this knowledge gap by reviewing current approaches to text-to-KG alignment and evaluating them on two datasets where manually created graphs are available, providing insights into the effectiveness of current methods.

Abstract: An emerging solution for explaining Transformer-based models is to use vector-based analysis on how the representations are formed. However, providing a faithful vector-based explanation for a multi-layer model could be challenging in three aspects: (1) Incorporating all components into the analysis, (2) Aggregating the layer dynamics to determine the information flow and mixture throughout the entire model, and (3) Identifying the connection between the vector-based analysis and the model's predictions. In this paper, we present DecompX to tackle these challenges. DecompX is based on the construction of decomposed token representations and their successive propagation throughout the model without mixing them in between layers. Additionally, our proposal provides multiple advantages over existing solutions for its inclusion of all encoder components (especially nonlinear feed-forward networks) and the classification head. The former allows acquiring precise vectors while the latter transforms the decomposition into meaningful prediction-based values, eliminating the need for norm- or summation-based vector aggregation. According to the standard faithfulness evaluations, DecompX consistently outperforms existing gradient-based and vector-based approaches on various datasets. Our code is available at https://github.com/mohsenfayyaz/DecompX.

Abstract: Whisper, the recently developed multilingual weakly supervised model, is reported to perform well on multiple speech recognition benchmarks in both monolingual and multilingual settings. However, it is not clear how Whisper would fare under diverse conditions even on languages it was evaluated on such as Arabic. In this work, we address this gap by comprehensively evaluating Whisper on several varieties of Arabic speech for the ASR task. Our evaluation covers most publicly available Arabic speech data and is performed under n-shot (zero-, few-, and full) finetuning. We also investigate the robustness of Whisper under completely novel conditions, such as in dialect-accented standard Arabic and in unseen dialects for which we develop evaluation data. Our experiments show that although Whisper zero-shot outperforms fully finetuned XLS-R models on all datasets, its performance deteriorates significantly in the zero-shot setting for five unseen dialects (i.e., Algeria, Jordan, Palestine, UAE, and Yemen).

Abstract: Large language models (LLMs) have already revolutionized code generation, after being pretrained on publicly available code data. However, while various methods have been proposed to augment LLMs with retrieved knowledge and enhance the quality of code generation, the performance of these retrieval-based methods is limited by the strength of the retrievers used. In addition, while LLMs show great emergent ability, they still struggle to produce the correct code in one turn. To address these challenges, we propose a novel two-step pipeline, called \autoknow, that leverages LLMs as both knowledge providers and self-reflective programmers. Unlike retrieval-based methods, \autoknow~obtains the knowledge from input prompts and generates intermediate code based on the generated knowledge. After that, \autoknow~asks LLM to act as an expert programmer to perform debugging for the generated code. This is achieved by receiving the error message from the interpreter, without requiring special test cases for correctness verification. We evaluate \autoknow~on three code generation datasets, including DS-1000 for data science code, HumanEval for software engineering code, and TransCoder for C++-to-Python translation. Our empirical experiments show that \autoknow~outperforms strong baselines by a significant margin on all datasets. We also conduct exhaustive analytical experiments to validate the effectiveness of the two stages of \autoknow, and find that both are superior to other prompting-based methods. Further scalability analysis demonstrates that \autoknow~can be adapted to other more advanced models, such as GPT-4, and bring consistent efficacy improvement.

Abstract: With the success of neural language models (LMs), their language acquisition has gained much attention. This work sheds light on the second language (L2) acquisition of LMs, while previous work has typically explored their first language (L1) acquisition. Specifically, we trained bilingual LMs with a scenario similar to human L2 acquisition and analyzed their cross-lingual transfer from linguistic perspectives. Our exploratory experiments demonstrated that the L1 pretraining accelerated their linguistic generalization in L2, and language transfer configurations (e.g., the L1 choice, and presence of parallel texts) substantially affected their generalizations. These clarify their (non-)human-like L2 acquisition in particular aspects.

Abstract: Most medical dialogue systems assume that patients have clear goals (medicine querying, surgical operation querying, etc.) before medical consultation. However, in many real scenarios, due to the lack of medical knowledge, it is usually difficult for patients to determine clear goals with all necessary slots. In this paper, we identify this challenge as how to construct medical consultation dialogue systems to help patients clarify their goals. To mitigate this challenge, we propose a novel task and create a human-to-human mixed-type medical consultation dialogue corpus, termed MidMed, covering five dialogue types: task-oriented dialogue for diagnosis, recommendation, knowledge-grounded dialogue, QA, and chitchat. MidMed covers four departments (otorhinolaryngology, ophthalmology, skin, and digestive system), with 8,175 dialogues. Furthermore, we build baselines on MidMed and propose an instruction-guiding medical dialogue generation framework, termed InsMed, to address this task. Experimental results show the effectiveness of InsMed.

Abstract: Social media is one of the most highly sought resources for analyzing characteristics of the language by its users. In particular, many researchers utilized various linguistic features of mental health problems from social media. However, existing approaches to detecting mental disorders face critical challenges, such as the scarcity of high-quality data or the trade-off between addressing the complexity of models and presenting interpretable results grounded in expert domain knowledge. To address these challenges, we design a simple but flexible model that preserves domain-based interpretability. We propose a novel approach that captures the semantic meanings directly from the text and compares them to symptom-related descriptions. Experimental results demonstrate that our model outperforms relevant baselines on various mental disorder detection tasks. Our detailed analysis shows that the proposed model is effective at leveraging domain knowledge, transferable to other mental disorders, and providing interpretable detection results.

Abstract: With the increasing diversity of use cases of large language models, a more informative treatment of texts seems necessary. An argumentative analysis could foster a more reasoned usage of chatbots, text completion mechanisms or other applications. However, it is unclear which aspects of argumentation can be reliably identified and integrated in language models. In this paper, we present an empirical assessment of the reliability with which different argumentative aspects can be automatically identified in hate speech in social media. We have enriched the Hateval corpus (Basile et al. 2019) with a manual annotation of some argumentative components, adapted from Wagemans (2016)'s Periodic Table of Arguments. We show that some components can be identified with reasonable reliability. For those that present a high error ratio, we analyze the patterns of disagreement between expert annotators and errors in automatic procedures, and we propose adaptations of those categories that can be more reliably reproduced.

Abstract: While recent works have been considerably improving the quality of the natural language explanations (NLEs) generated by a model to justify its predictions, there is very limited research in detecting and alleviating inconsistencies among generated NLEs. In this work, we leverage external knowledge bases to significantly improve on an existing adversarial attack for detecting inconsistent NLEs. We apply our attack to high-performing NLE models and show that models with higher NLE quality do not necessarily generate fewer inconsistencies. Moreover, we propose an off-the-shelf mitigation method to alleviate inconsistencies by grounding the model into external background knowledge. Our method decreases the inconsistencies of previous high-performing NLE models as detected by our attack.

Abstract: We propose PolyVoice, a language model-based framework for speech-to-speech translation (S2ST) system. Our framework consists of two language models: a translation language model and a speech synthesis language model. We use discretized speech units, which are generated in a fully unsupervised way, and thus our framework can be used for unwritten languages. For the speech synthesis part, we adopt the existing VALL-E X approach and build a unit-based audio language model. This grants our framework the ability to preserve the voice characteristics and the speaking style of the original speech. We examine our system on Chinese $\rightarrow$ English and English $\rightarrow$ Spanish pairs. Experimental results show that our system can generate speech with high translation quality and audio quality. Speech samples are available at https://speechtranslation.github.io/polyvoice.

Abstract: The recently released ChatGPT model demonstrates unprecedented capabilities in zero-shot question-answering. In this work, we probe ChatGPT for its conversational understanding and introduce a conversational framework (protocol) that can be adopted in future studies. The Pok\'emon universe serves as an ideal testing ground for auditing ChatGPT's reasoning capabilities due to its closed world assumption. After bringing ChatGPT's background knowledge (on the Pok\'emon universe) to light, we test its reasoning process when using these concepts in battle scenarios. We then evaluate its ability to acquire new knowledge and include it in its reasoning process. Our ultimate goal is to assess ChatGPT's ability to generalize, combine features, and to acquire and reason over newly introduced knowledge from human feedback. We find that ChatGPT has prior knowledge of the Pokemon universe, which can reason upon in battle scenarios to a great extent, even when new information is introduced. The model performs better with collaborative feedback and if there is an initial phase of information retrieval, but also hallucinates occasionally and is susceptible to adversarial attacks.

Abstract: Recent advancements in large language models (LLMs) have transformed the field of question answering (QA). However, evaluating LLMs in the medical field is challenging due to the lack of standardized and comprehensive datasets. To address this gap, we introduce CMExam, sourced from the Chinese National Medical Licensing Examination. CMExam consists of 60K+ multiple-choice questions for standardized and objective evaluations, as well as solution explanations for model reasoning evaluation in an open-ended manner. For in-depth analyses of LLMs, we invited medical professionals to label five additional question-wise annotations, including disease groups, clinical departments, medical disciplines, areas of competency, and question difficulty levels. Alongside the dataset, we further conducted thorough experiments with representative LLMs and QA algorithms on CMExam. The results show that GPT-4 had the best accuracy of 61.5% and a weighted F1 score of 0.616. These results highlight a great disparity when compared to human accuracy, which stood at 71.6%. For explanation tasks, while LLMs could generate relevant reasoning and demonstrate improved performance after finetuning, they fall short of a desired standard, indicating ample room for improvement. To the best of our knowledge, CMExam is the first Chinese medical exam dataset to provide comprehensive medical annotations. The experiments and findings of LLM evaluation also provide valuable insights into the challenges and potential solutions in developing Chinese medical QA systems and LLM evaluation pipelines. The dataset and relevant code are available at https://github.com/williamliujl/CMExam.

Abstract: Using Japanese honorifics is challenging because it requires not only knowledge of the grammatical rules but also contextual information, such as social relationships. It remains unclear whether pre-trained large language models (LLMs) can flexibly handle Japanese honorifics like humans. To analyze this, we introduce an honorific conversion task that considers social relationships among people mentioned in a conversation. We construct a Japanese honorifics dataset from problem templates of various sentence structures to investigate the syntactic generalization capacity of GPT-3, one of the leading LLMs, on this task under two settings: fine-tuning and prompt learning. Our results showed that the fine-tuned GPT-3 performed better in a context-aware honorific conversion task than the prompt-based one. The fine-tuned model demonstrated overall syntactic generalizability towards compound honorific sentences, except when tested with the data involving direct speech.

Abstract: Recently, there has been a growing interest in the development of gradient-based sampling algorithms for text generation, especially in the context of controlled generation. However, there exists a lack of theoretically grounded and principled approaches for this task. In this paper, we take an important step toward building a principled approach for sampling from language models with gradient-based methods. We use discrete distributions given by language models to define densities and develop an algorithm based on Hamiltonian Monte Carlo to sample from them. We name our gradient-based technique Structured Voronoi Sampling (SVS). In an experimental setup where the reference distribution is known, we show that the empirical distribution of SVS samples is closer to the reference distribution compared to alternative sampling schemes. Furthermore, in a controlled generation task, SVS is able to generate fluent and diverse samples while following the control targets significantly better than other methods.

Abstract: Summarizing lengthy documents is a common and essential task in our daily lives. Although recent advancements in neural summarization models can assist in crafting general-purpose summaries, human writers often have specific requirements that call for a more customized approach. To address this need, we introduce REVISE (Refinement and Editing via Iterative Summarization Enhancement), an innovative framework designed to facilitate iterative editing and refinement of draft summaries by human writers. Within our framework, writers can effortlessly modify unsatisfactory segments at any location or length and provide optional starting phrases -- our system will generate coherent alternatives that seamlessly integrate with the existing summary. At its core, REVISE incorporates a modified fill-in-the-middle model with the encoder-decoder architecture while developing novel evaluation metrics tailored for the summarization task. In essence, our framework empowers users to create high-quality, personalized summaries by effectively harnessing both human expertise and AI capabilities, ultimately transforming the summarization process into a truly collaborative and adaptive experience.

Abstract: Recent advances in large language model (LLM) pretraining have led to high-quality LLMs with impressive abilities. By compressing such LLMs via quantization to 3-4 bits per parameter, they can fit into memory-limited devices such as laptops and mobile phones, enabling personalized use. However, quantization down to 3-4 bits per parameter usually leads to moderate-to-high accuracy losses, especially for smaller models in the 1-10B parameter range, which are well-suited for edge deployments. To address this accuracy issue, we introduce the Sparse-Quantized Representation (SpQR), a new compressed format and quantization technique which enables for the first time near-lossless compression of LLMs across model scales, while reaching similar compression levels to previous methods. SpQR works by identifying and isolating outlier weights, which cause particularly-large quantization errors, and storing them in higher precision, while compressing all other weights to 3-4 bits, and achieves relative accuracy losses of less than 1% in perplexity for highly-accurate LLaMA and Falcon LLMs. This makes it possible to run 33B parameter LLM on a single 24 GB consumer GPU without any performance degradation at 15% speedup thus making powerful LLMs available to consumer without any downsides. SpQR comes with efficient algorithms for both encoding weights into its format, as well as decoding them efficiently at runtime. Specifically, we provide an efficient GPU inference algorithm for SpQR which yields faster inference than 16-bit baselines at similar accuracy, while enabling memory compression gains of more than 4x.

Abstract: Mapping political party systems to metric policy spaces is one of the major methodological problems in political science. At present, in most political science project this task is performed by domain experts relying on purely qualitative assessments, with all the attendant problems of subjectivity and labor intensiveness. We consider how advances in natural language processing, including large transformer-based language models, can be applied to solve that issue. We apply a number of texts similarity measures to party political programs, analyze how they correlate with each other, and -- in the absence of a satisfactory benchmark -- evaluate them against other measures, including those based on expert surveys, voting records, electoral patterns, and candidate networks. Finally, we consider the prospects of relying on those methods to correct, supplement, and eventually replace expert judgments.

Abstract: Coaching, which involves classroom observation and expert feedback, is a widespread and fundamental part of teacher training. However, the majority of teachers do not have access to consistent, high quality coaching due to limited resources and access to expertise. We explore whether generative AI could become a cost-effective complement to expert feedback by serving as an automated teacher coach. In doing so, we propose three teacher coaching tasks for generative AI: (A) scoring transcript segments based on classroom observation instruments, (B) identifying highlights and missed opportunities for good instructional strategies, and (C) providing actionable suggestions for eliciting more student reasoning. We recruit expert math teachers to evaluate the zero-shot performance of ChatGPT on each of these tasks for elementary math classroom transcripts. Our results reveal that ChatGPT generates responses that are relevant to improving instruction, but they are often not novel or insightful. For example, 82% of the model's suggestions point to places in the transcript where the teacher is already implementing that suggestion. Our work highlights the challenges of producing insightful, novel and truthful feedback for teachers while paving the way for future research to address these obstacles and improve the capacity of generative AI to coach teachers.

Abstract: Large Language Models (LLMs) have greatly advanced code auto-completion systems, with a potential for substantial productivity enhancements for developers. However, current benchmarks mainly focus on single-file tasks, leaving an assessment gap for more complex, real-world, multi-file programming scenarios. To fill this gap, we introduce RepoBench, a new benchmark specifically designed for evaluating repository-level code auto-completion systems. RepoBench consists of three interconnected evaluation tasks: RepoBench-R (Retrieval), RepoBench-C (Code Completion), and RepoBench-P (Pipeline). Each task respectively measures the system's ability to retrieve the most relevant code snippets from other files as cross-file context, predict the next line of code with cross-file and in-file context, and handle complex tasks that require a combination of both retrieval and next-line prediction. RepoBench aims to facilitate a more complete comparison of performance and encouraging continuous improvement in auto-completion systems. RepoBench is publicly available at https://github.com/Leolty/repobench.