Computation and Language (cs.CL)

Abstract: Recently, Instruction fine-tuning has risen to prominence as a potential method for enhancing the zero-shot capabilities of Large Language Models (LLMs) on novel tasks. This technique has shown an exceptional ability to boost the performance of moderately sized LLMs, sometimes even reaching performance levels comparable to those of much larger model variants. The focus is on the robustness of instruction-tuned LLMs to seen and unseen tasks. We conducted an exploration of six models including Alpaca, Vicuna, WizardLM, and Traditional Task-oriented Models(Flan-T5-XL/XXL, T0++) using real-world relation extraction datasets as case studies. We carried out a comprehensive evaluation of these instruction-following LLMs which have been tuned based on open-domain instructions and task-oriented instructions. The main discussion is their performance and robustness towards instructions. We have observed that in most cases, the model's performance in dealing with unfamiliar instructions tends to worsen significantly, and the robustness of the model for RE instructions deteriorates compared to QA. Further, we discovered that up until a certain parameter size threshold (3B), the performance of the FLAN-T5 model improves as the parameter count increases. The robustness of different scales of FLAN-T5 models to RE instruction is worse than the robustness to QA instruction.

Abstract: Electronic Health Records (EHRs) and routine documentation practices play a vital role in patients' daily care, providing a holistic record of health, diagnoses, and treatment. However, complex and verbose EHR narratives overload healthcare providers, risking diagnostic inaccuracies. While Large Language Models (LLMs) have showcased their potential in diverse language tasks, their application in the healthcare arena needs to ensure the minimization of diagnostic errors and the prevention of patient harm. In this paper, we outline an innovative approach for augmenting the proficiency of LLMs in the realm of automated diagnosis generation, achieved through the incorporation of a medical knowledge graph (KG) and a novel graph model: Dr.Knows, inspired by the clinical diagnostic reasoning process. We derive the KG from the National Library of Medicine's Unified Medical Language System (UMLS), a robust repository of biomedical knowledge. Our method negates the need for pre-training and instead leverages the KG as an auxiliary instrument aiding in the interpretation and summarization of complex medical concepts. Using real-world hospital datasets, our experimental results demonstrate that the proposed approach of combining LLMs with KG has the potential to improve the accuracy of automated diagnosis generation. More importantly, our approach offers an explainable diagnostic pathway, edging us closer to the realization of AI-augmented diagnostic decision support systems.

Abstract: We propose DISC-MedLLM, a comprehensive solution that leverages Large Language Models (LLMs) to provide accurate and truthful medical response in end-to-end conversational healthcare services. To construct high-quality Supervised Fine-Tuning (SFT) datasets, we employ three strategies: utilizing medical knowledge-graphs, reconstructing real-world dialogues, and incorporating human-guided preference rephrasing. These datasets are instrumental in training DISC-MedLLM, surpassing existing medical LLMs in both single-turn and multi-turn consultation scenarios. Extensive experimental results demonstrate the effectiveness of the proposed model in bridging the gap between general language models and real-world medical consultation. Additionally, we release the constructed dataset and model weights to further contribute to research and development. Further details and resources can be found at https://github.com/FudanDISC/DISC-MedLLM

Abstract: The unprecedented performance of large language models (LLMs) requires comprehensive and accurate evaluation. We argue that for LLMs evaluation, benchmarks need to be comprehensive and systematic. To this end, we propose the ZhuJiu benchmark, which has the following strengths: (1) Multi-dimensional ability coverage: We comprehensively evaluate LLMs across 7 ability dimensions covering 51 tasks. Especially, we also propose a new benchmark that focuses on knowledge ability of LLMs. (2) Multi-faceted evaluation methods collaboration: We use 3 different yet complementary evaluation methods to comprehensively evaluate LLMs, which can ensure the authority and accuracy of the evaluation results. (3) Comprehensive Chinese benchmark: ZhuJiu is the pioneering benchmark that fully assesses LLMs in Chinese, while also providing equally robust evaluation abilities in English. (4) Avoiding potential data leakage: To avoid data leakage, we construct evaluation data specifically for 37 tasks. We evaluate 10 current mainstream LLMs and conduct an in-depth discussion and analysis of their results. The ZhuJiu benchmark and open-participation leaderboard are publicly released at http://www.zhujiu-benchmark.com/ and we also provide a demo video at https://youtu.be/qypkJ89L1Ic.

Abstract: Document-level relation extraction aims to identify relationships between entities within a document. Current methods rely on text-based encoders and employ various hand-coded pooling heuristics to aggregate information from entity mentions and associated contexts. In this paper, we replace these rigid pooling functions with explicit graph relations by leveraging the intrinsic graph processing capabilities of the Transformer model. We propose a joint text-graph Transformer model, and a graph-assisted declarative pooling (GADePo) specification of the input which provides explicit and high-level instructions for information aggregation. This allows the pooling process to be guided by domain-specific knowledge or desired outcomes but still learned by the Transformer, leading to more flexible and customizable pooling strategies. We extensively evaluate our method across diverse datasets and models, and show that our approach yields promising results that are comparable to those achieved by the hand-coded pooling functions.

Abstract: Linking biomedical entities is an essential aspect in biomedical natural language processing tasks, such as text mining and question answering. However, a difficulty of linking the biomedical entities using current large language models (LLM) trained on a general corpus is that biomedical entities are scarcely distributed in texts and therefore have been rarely seen during training by the LLM. At the same time, those LLMs are not aware of high level semantic connection between different biomedical entities, which are useful in identifying similar concepts in different textual contexts. To cope with aforementioned problems, some recent works focused on injecting knowledge graph information into LLMs. However, former methods either ignore the relational knowledge of the entities or lead to catastrophic forgetting. Therefore, we propose a novel framework to pre-train the powerful generative LLM by a corpus synthesized from a KG. In the evaluations we are unable to confirm the benefit of including synonym, description or relational information.

Abstract: Knowledge Base Question Answering (KBQA) aims to answer natural language questions with factual information such as entities and relations in KBs. However, traditional Pre-trained Language Models (PLMs) are directly pre-trained on large-scale natural language corpus, which poses challenges for them in understanding and representing complex subgraphs in structured KBs. To bridge the gap between texts and structured KBs, we propose a Structured Knowledge-aware Pre-training method (SKP). In the pre-training stage, we introduce two novel structured knowledge-aware tasks, guiding the model to effectively learn the implicit relationship and better representations of complex subgraphs. In downstream KBQA task, we further design an efficient linearization strategy and an interval attention mechanism, which assist the model to better encode complex subgraphs and shield the interference of irrelevant subgraphs during reasoning respectively. Detailed experiments and analyses on WebQSP verify the effectiveness of SKP, especially the significant improvement in subgraph retrieval (+4.08% H@10).

Abstract: Consistency regularization methods, such as R-Drop (Liang et al., 2021) and CrossConST (Gao et al., 2023), have achieved impressive supervised and zero-shot performance in the neural machine translation (NMT) field. Can we also boost end-to-end (E2E) speech-to-text translation (ST) by leveraging consistency regularization? In this paper, we conduct empirical studies on intra-modal and cross-modal consistency and propose two training strategies, SimRegCR and SimZeroCR, for E2E ST in regular and zero-shot scenarios. Experiments on the MuST-C benchmark show that our approaches achieve state-of-the-art (SOTA) performance in most translation directions. The analyses prove that regularization brought by the intra-modal consistency, instead of modality gap, is crucial for the regular E2E ST, and the cross-modal consistency could close the modality gap and boost the zero-shot E2E ST performance.

Abstract: Although not all bots are malicious, the vast majority of them are responsible for spreading misinformation and manipulating the public opinion about several issues, i.e., elections and many more. Therefore, the early detection of social spambots is crucial. Although there have been proposed methods for detecting bots in social media, there are still substantial limitations. For instance, existing research initiatives still extract a large number of features and train traditional machine learning algorithms or use GloVe embeddings and train LSTMs. However, feature extraction is a tedious procedure demanding domain expertise. Also, language models based on transformers have been proved to be better than LSTMs. Other approaches create large graphs and train graph neural networks requiring in this way many hours for training and access to computational resources. To tackle these limitations, this is the first study employing only the user description field and images of three channels denoting the type and content of tweets posted by the users. Firstly, we create digital DNA sequences, transform them to 3d images, and apply pretrained models of the vision domain, including EfficientNet, AlexNet, VGG16, etc. Next, we propose a multimodal approach, where we use TwHIN-BERT for getting the textual representation of the user description field and employ VGG16 for acquiring the visual representation for the image modality. We propose three different fusion methods, namely concatenation, gated multimodal unit, and crossmodal attention, for fusing the different modalities and compare their performances. Extensive experiments conducted on the Cresci '17 dataset demonstrate valuable advantages of our introduced approaches over state-of-the-art ones reaching Accuracy up to 99.98%.

Abstract: Although large language models (LLMs) demonstrate impressive performance for many language tasks, most of them can only handle texts a few thousand tokens long, limiting their applications on longer sequence inputs, such as books, reports, and codebases. Recent works have proposed methods to improve LLMs' long context capabilities by extending context windows and more sophisticated memory mechanisms. However, comprehensive benchmarks tailored for evaluating long context understanding are lacking. In this paper, we introduce LongBench, the first bilingual, multi-task benchmark for long context understanding, enabling a more rigorous evaluation of long context understanding. LongBench comprises 21 datasets across 6 task categories in both English and Chinese, with an average length of 6,711 words (English) and 13,386 characters (Chinese). These tasks cover key long-text application areas including single-doc QA, multi-doc QA, summarization, few-shot learning, synthetic tasks, and code completion. All datasets in LongBench are standardized into a unified format, allowing for effortless automatic evaluation of LLMs. Upon comprehensive evaluation of 8 LLMs on LongBench, we find that: (1) Commercial model (GPT-3.5-Turbo-16k) outperforms other open-sourced models, but still struggles on longer contexts. (2) Scaled position embedding and fine-tuning on longer sequences lead to substantial improvement on long context understanding. (3) Context compression technique such as retrieval brings improvement for model with weak ability on long contexts, but the performance still lags behind models that have strong long context understanding capability. The code and datasets are available at https://github.com/THUDM/LongBench.

Abstract: The objective of few-shot named entity recognition is to identify named entities with limited labeled instances. Previous works have primarily focused on optimizing the traditional token-wise classification framework, while neglecting the exploration of information based on NER data characteristics. To address this issue, we propose a Multi-Task Semantic Decomposition Framework via Joint Task-specific Pre-training (MSDP) for few-shot NER. Drawing inspiration from demonstration-based and contrastive learning, we introduce two novel pre-training tasks: Demonstration-based Masked Language Modeling (MLM) and Class Contrastive Discrimination. These tasks effectively incorporate entity boundary information and enhance entity representation in Pre-trained Language Models (PLMs). In the downstream main task, we introduce a multi-task joint optimization framework with the semantic decomposing method, which facilitates the model to integrate two different semantic information for entity classification. Experimental results of two few-shot NER benchmarks demonstrate that MSDP consistently outperforms strong baselines by a large margin. Extensive analyses validate the effectiveness and generalization of MSDP.

Abstract: People have long hoped for a conversational system that can assist in real-life situations, and recent progress on large language models (LLMs) is bringing this idea closer to reality. While LLMs are often impressive in performance, their efficacy in real-world scenarios that demand expert knowledge remains unclear. LLMs are believed to hold the most potential and value in education, especially in the development of Artificial intelligence (AI) based virtual teachers capable of facilitating language learning. Our focus is centered on evaluating the efficacy of LLMs in the realm of education, specifically in the areas of spoken language learning which encompass phonetics, phonology, and second language acquisition. We introduce a new multiple-choice question dataset to evaluate the effectiveness of LLMs in the aforementioned scenarios, including understanding and application of spoken language knowledge. In addition, we investigate the influence of various prompting techniques such as zero- and few-shot method (prepending the question with question-answer exemplars), chain-of-thought (CoT, think step-by-step), in-domain exampler and external tools (Google, Wikipedia). We conducted large-scale evaluation on popular LLMs (20 distinct models) using these methods. We achieved significant performance improvements compared to the zero-shot baseline in the practical questions reasoning (GPT-3.5, 49.1% -> 63.1%; LLaMA2-70B-Chat, 42.2% -> 48.6%). We found that models of different sizes have good understanding of concepts in phonetics, phonology, and second language acquisition, but show limitations in reasoning for real-world problems. Additionally, we also explore preliminary findings on conversational communication.

Abstract: We propose the use of conversational GPT models for easy and quick few-shot text classification in the financial domain using the Banking77 dataset. Our approach involves in-context learning with GPT-3.5 and GPT-4, which minimizes the technical expertise required and eliminates the need for expensive GPU computing while yielding quick and accurate results. Additionally, we fine-tune other pre-trained, masked language models with SetFit, a recent contrastive learning technique, to achieve state-of-the-art results both in full-data and few-shot settings. Our findings show that querying GPT-3.5 and GPT-4 can outperform fine-tuned, non-generative models even with fewer examples. However, subscription fees associated with these solutions may be considered costly for small organizations. Lastly, we find that generative models perform better on the given task when shown representative samples selected by a human expert rather than when shown random ones. We conclude that a) our proposed methods offer a practical solution for few-shot tasks in datasets with limited label availability, and b) our state-of-the-art results can inspire future work in the area.

Abstract: The potential to provide patients with faster information access while allowing medical specialists to concentrate on critical tasks makes medical domain dialog agents appealing. However, the integration of large-language models (LLMs) into these agents presents certain limitations that may result in serious consequences. This paper investigates the challenges and risks of using GPT-3-based models for medical question-answering (MedQA). We perform several evaluations contextualized in terms of standard medical principles. We provide a procedure for manually designing patient queries to stress-test high-risk limitations of LLMs in MedQA systems. Our analysis reveals that LLMs fail to respond adequately to these queries, generating erroneous medical information, unsafe recommendations, and content that may be considered offensive.

Abstract: Multiple intent detection and slot filling are two fundamental and crucial tasks in spoken language understanding. Motivated by the fact that the two tasks are closely related, joint models that can detect intents and extract slots simultaneously are preferred to individual models that perform each task independently. The accuracy of a joint model depends heavily on the ability of the model to transfer information between the two tasks so that the result of one task can correct the result of the other. In addition, since a joint model has multiple outputs, how to train the model effectively is also challenging. In this paper, we present a method for multiple intent detection and slot filling by addressing these challenges. First, we propose a bidirectional joint model that explicitly employs intent information to recognize slots and slot features to detect intents. Second, we introduce a novel method for training the proposed joint model using supervised contrastive learning and self-distillation. Experimental results on two benchmark datasets MixATIS and MixSNIPS show that our method outperforms state-of-the-art models in both tasks. The results also demonstrate the contributions of both bidirectional design and the training method to the accuracy improvement. Our source code is available at https://github.com/anhtunguyen98/BiSLU

Abstract: One of the main tasks of Natural Language Processing (NLP), is Named Entity Recognition (NER). It is used in many applications and also can be used as an intermediate step for other tasks. We present ANER, a web-based named entity recognizer for the Arabic, and Arabizi languages. The model is built upon BERT, which is a transformer-based encoder. It can recognize 50 different entity classes, covering various fields. We trained our model on the WikiFANE\_Gold dataset which consists of Wikipedia articles. We achieved an F1 score of 88.7\%, which beats CAMeL Tools' F1 score of 83\% on the ANERcorp dataset, which has only 4 classes. We also got an F1 score of 77.7\% on the NewsFANE\_Gold dataset which contains out-of-domain data from News articles. The system is deployed on a user-friendly web interface that accepts users' inputs in Arabic, or Arabizi. It allows users to explore the entities in the text by highlighting them. It can also direct users to get information about entities through Wikipedia directly. We added the ability to do NER using our model, or CAMeL Tools' model through our website. ANER is publicly accessible at \url{http://www.aner.online}. We also deployed our model on HuggingFace at https://huggingface.co/boda/ANER, to allow developers to test and use it.

Abstract: Detecting online sexual predatory behaviours and abusive language on social media platforms has become a critical area of research due to the growing concerns about online safety, especially for vulnerable populations such as children and adolescents. Researchers have been exploring various techniques and approaches to develop effective detection systems that can identify and mitigate these risks. Recent development of large language models (LLMs) has opened a new opportunity to address this problem more effectively. This paper proposes an approach to detection of online sexual predatory chats and abusive language using the open-source pretrained Llama 2 7B-parameter model, recently released by Meta GenAI. We fine-tune the LLM using datasets with different sizes, imbalance degrees, and languages (i.e., English, Roman Urdu and Urdu). Based on the power of LLMs, our approach is generic and automated without a manual search for a synergy between feature extraction and classifier design steps like conventional methods in this domain. Experimental results show a strong performance of the proposed approach, which performs proficiently and consistently across three distinct datasets with five sets of experiments. This study's outcomes indicate that the proposed method can be implemented in real-world applications (even with non-English languages) for flagging sexual predators, offensive or toxic content, hate speech, and discriminatory language in online discussions and comments to maintain respectful internet or digital communities. Furthermore, it can be employed for solving text classification problems with other potential applications such as sentiment analysis, spam and phishing detection, sorting legal documents, fake news detection, language identification, user intent recognition, text-based product categorization, medical record analysis, and resume screening.