Computation and Language (cs.CL)

Abstract: In clinical dictation, utterances after automatic speech recognition (ASR) without explicit punctuation marks may lead to the misunderstanding of dictated reports. To give a precise and understandable clinical report with ASR, automatic punctuation restoration is required. Considering a practical scenario, we propose a fast and light pre-trained model for Chinese medical punctuation restoration based on 'pretraining and fine-tuning' paradigm. In this work, we distill pre-trained models by incorporating supervised contrastive learning and a novel auxiliary pre-training task (Punctuation Mark Prediction) to make it well-suited for punctuation restoration. Our experiments on various distilled models reveal that our model can achieve 95% performance while 10% model size relative to state-of-the-art Chinese RoBERTa.

Abstract: Recent researches indicate that Pre-trained Large Language Models (LLMs) possess cognitive constructs similar to those observed in humans, prompting researchers to investigate the cognitive aspects of LLMs. This paper focuses on explicit and implicit social bias, a distinctive two-level cognitive construct in psychology. It posits that individuals' explicit social bias, which is their conscious expression of bias in the statements, may differ from their implicit social bias, which represents their unconscious bias. We propose a two-stage approach and discover a parallel phenomenon in LLMs known as "re-judge inconsistency" in social bias. In the initial stage, the LLM is tasked with automatically completing statements, potentially incorporating implicit social bias. However, in the subsequent stage, the same LLM re-judges the biased statement generated by itself but contradicts it. We propose that this re-judge inconsistency can be similar to the inconsistency between human's unaware implicit social bias and their aware explicit social bias. Experimental investigations on ChatGPT and GPT-4 concerning common gender biases examined in psychology corroborate the highly stable nature of the re-judge inconsistency. This finding may suggest that diverse cognitive constructs emerge as LLMs' capabilities strengthen. Consequently, leveraging psychological theories can provide enhanced insights into the underlying mechanisms governing the expressions of explicit and implicit constructs in LLMs.

Abstract: This paper presents a set of industrial-grade text processing models for Hungarian that achieve near state-of-the-art performance while balancing resource efficiency and accuracy. Models have been implemented in the spaCy framework, extending the HuSpaCy toolkit with several improvements to its architecture. Compared to existing NLP tools for Hungarian, all of our pipelines feature all basic text processing steps including tokenization, sentence-boundary detection, part-of-speech tagging, morphological feature tagging, lemmatization, dependency parsing and named entity recognition with high accuracy and throughput. We thoroughly evaluated the proposed enhancements, compared the pipelines with state-of-the-art tools and demonstrated the competitive performance of the new models in all text preprocessing steps. All experiments are reproducible and the pipelines are freely available under a permissive license.

Abstract: In this paper I propose a new way of measuring linguistic productivity that objectively assesses the ability of an affix to be used to coin new complex words and, unlike other popular measures, is not directly dependent upon token frequency. Specifically, I suggest that linguistic productivity may be viewed as the probability of an affix to combine with a random base. The advantages of this approach include the following. First, token frequency does not dominate the productivity measure but naturally influences the sampling of bases. Second, we are not just counting attested word types with an affix but rather simulating the construction of these types and then checking whether they are attested in the corpus. Third, a corpus-based approach and randomised design assure that true neologisms and words coined long ago have equal chances to be selected. The proposed algorithm is evaluated both on English and Russian data. The obtained results provide some valuable insights into the relation of linguistic productivity to the number of types and tokens. It looks like burgeoning linguistic productivity manifests itself in an increasing number of types. However, this process unfolds in two stages: first comes the increase in high-frequency items, and only then follows the increase in low-frequency items.

Abstract: Emotion recognition in conversations (ERC) is a crucial task for building human-like conversational agents. While substantial efforts have been devoted to ERC for chit-chat dialogues, the task-oriented counterpart is largely left unattended. Directly applying chit-chat ERC models to task-oriented dialogues (ToDs) results in suboptimal performance as these models overlook key features such as the correlation between emotions and task completion in ToDs. In this paper, we propose a framework that turns a chit-chat ERC model into a task-oriented one, addressing three critical aspects: data, features and objective. First, we devise two ways of augmenting rare emotions to improve ERC performance. Second, we use dialogue states as auxiliary features to incorporate key information from the goal of the user. Lastly, we leverage a multi-aspect emotion definition in ToDs to devise a multi-task learning objective and a novel emotion-distance weighted loss function. Our framework yields significant improvements for a range of chit-chat ERC models on EmoWOZ, a large-scale dataset for user emotion in ToDs. We further investigate the generalisability of the best resulting model to predict user satisfaction in different ToD datasets. A comparison with supervised baselines shows a strong zero-shot capability, highlighting the potential usage of our framework in wider scenarios.

Abstract: Large Language Models (LLMs) present strong general capabilities, and a current compelling challenge is stimulating their specialized capabilities, such as machine translation, through low-cost instruction tuning. The standard instruction-following data is sequentially organized as the concatenation of an instruction, an input, and a response. As the attention mechanism of LLMs has limitations on local focus, LLMs tend to focus more on the words or sentences nearby at each position. This leads to a high risk of instruction forgetting during decoding. To alleviate the above issues, We propose SWIE (Segment-Weighted Instruction Embedding) and an instruction-following dataset OVERMISS. SWIE improves the model instruction understanding by adding a global instruction representation on the following input and response representations. OVERMISS improves model faithfulness by comparing over-translation and miss-translation results with the correct translation. We apply our methods to two main-stream open-source LLMs, BLOOM and LLaMA. The experimental results demonstrate significant improvements in translation performance with SWIE based on BLOOMZ-3b, particularly in zero-shot and long text translations due to reduced instruction forgetting risk. Additionally, OVERMISS outperforms the baseline in translation performance (e.g. an increase in BLEU scores from 0.69 to 3.12 and an average improvement of 0.48 percentage comet scores for LLaMA-7b) with further enhancements seen in models combining OVERMISS and SWIE (e.g. the BLUE scores increase up to 0.56 from English to German across three different backbones), and both exhibit improvements in the faithfulness metric based on word alignment.

Abstract: Instruction tuning is instrumental in enabling Large Language Models~(LLMs) to follow user instructions to complete various open-domain tasks. The success of instruction tuning depends on the availability of high-quality instruction data. Owing to the exorbitant cost and substandard quality of human annotation, recent works have been deeply engaged in the exploration of the utilization of powerful closed-source models to generate instruction data automatically. However, these methods carry potential risks arising from the usage requirements of powerful closed-source models, which strictly forbid the utilization of their outputs to develop machine learning models. To deal with this problem, in this work, we explore alternative approaches to generate high-quality instruction data that do not rely on closed-source models. Our exploration includes an investigation of various existing instruction generation methods, culminating in the integration of the most efficient variant with two novel strategies to enhance the quality further. Evaluation results from two benchmarks and the GPT-4 model demonstrate the effectiveness of our generated instruction data, which can outperform Alpaca, a method reliant on closed-source models. We hope that more progress can be achieved in generating high-quality instruction data without using closed-source models.

Abstract: Spurred by the recent rapid increase in the development and distribution of large language models (LLMs) across industry and academia, much recent work has drawn attention to safety- and security-related threats and vulnerabilities of LLMs, including in the context of potentially criminal activities. Specifically, it has been shown that LLMs can be misused for fraud, impersonation, and the generation of malware; while other authors have considered the more general problem of AI alignment. It is important that developers and practitioners alike are aware of security-related problems with such models. In this paper, we provide an overview of existing - predominantly scientific - efforts on identifying and mitigating threats and vulnerabilities arising from LLMs. We present a taxonomy describing the relationship between threats caused by the generative capabilities of LLMs, prevention measures intended to address such threats, and vulnerabilities arising from imperfect prevention measures. With our work, we hope to raise awareness of the limitations of LLMs in light of such security concerns, among both experienced developers and novel users of such technologies.

Abstract: Plagiarism detection is one of the most researched areas among the Natural Language Processing(NLP) community. A good plagiarism detection covers all the NLP methods including semantics, named entities, paraphrases etc. and produces detailed plagiarism reports. Detection of Cross Lingual Plagiarism requires deep knowledge of various advanced methods and algorithms to perform effective text similarity checking. Nowadays the plagiarists are also advancing themselves from hiding the identity from being catch in such offense. The plagiarists are bypassed from being detected with techniques like paraphrasing, synonym replacement, mismatching citations, translating one language to another. Image Content Plagiarism Detection (ICPD) has gained importance, utilizing advanced image content processing to identify instances of plagiarism to ensure the integrity of image content. The issue of plagiarism extends beyond textual content, as images such as figures, graphs, and tables also have the potential to be plagiarized. However, image content plagiarism detection remains an unaddressed challenge. Therefore, there is a critical need to develop methods and systems for detecting plagiarism in image content. In this paper, the system has been implemented to detect plagiarism form contents of Images such as Figures, Graphs, Tables etc. Along with statistical algorithms such as Jaccard and Cosine, introducing semantic algorithms such as LSA, BERT, WordNet outperformed in detecting efficient and accurate plagiarism.

Abstract: The mainstream of data-driven abstractive summarization models tends to explore the correlations rather than the causal relationships. Among such correlations, there can be spurious ones which suffer from the language prior learned from the training corpus and therefore undermine the overall effectiveness of the learned model. To tackle this issue, we introduce a Structural Causal Model (SCM) to induce the underlying causal structure of the summarization data. We assume several latent causal factors and non-causal factors, representing the content and style of the document and summary. Theoretically, we prove that the latent factors in our SCM can be identified by fitting the observed training data under certain conditions. On the basis of this, we propose a Causality Inspired Sequence-to-Sequence model (CI-Seq2Seq) to learn the causal representations that can mimic the causal factors, guiding us to pursue causal information for summary generation. The key idea is to reformulate the Variational Auto-encoder (VAE) to fit the joint distribution of the document and summary variables from the training corpus. Experimental results on two widely used text summarization datasets demonstrate the advantages of our approach.

Abstract: The emergence of generative Large Language Models (LLMs) emphasizes the need for accurate and efficient prompting approaches. LLMs are often applied in Few-Shot Learning (FSL) contexts, where tasks are executed with minimal training data. FSL has become popular in many Artificial Intelligence (AI) subdomains, including AI for health. Rare diseases, affecting a small fraction of the population, inherently require FSL techniques due to limited data availability, though manual data collection and annotation is costly and time-consuming. In this paper, we propose Models-Vote Prompting (MVP), a flexible prompting approach for improving the performance of LLM queries in FSL settings. MVP works by prompting numerous LLMs to perform the same tasks and then conducting a majority vote on the resulting outputs. This method achieves improved results to any one model in the ensemble on one-shot rare disease identification and classification tasks. We also release a novel rare disease dataset for FSL, available to those who agreed to the MIMIC-IV Data Use Agreement (DUA). Furthermore, in using MVP, each model is prompted multiple times, substantially increasing the time needed for manual annotation, and to address this, we assess the feasibility of using JSON for automating generative LLM evaluation.

Abstract: We release Code Llama, a family of large language models for code based on Llama 2 providing state-of-the-art performance among open models, infilling capabilities, support for large input contexts, and zero-shot instruction following ability for programming tasks. We provide multiple flavors to cover a wide range of applications: foundation models (Code Llama), Python specializations (Code Llama - Python), and instruction-following models (Code Llama - Instruct) with 7B, 13B and 34B parameters each. All models are trained on sequences of 16k tokens and show improvements on inputs with up to 100k tokens. 7B and 13B Code Llama and Code Llama - Instruct variants support infilling based on surrounding content. Code Llama reaches state-of-the-art performance among open models on several code benchmarks, with scores of up to 53% and 55% on HumanEval and MBPP, respectively. Notably, Code Llama - Python 7B outperforms Llama 2 70B on HumanEval and MBPP, and all our models outperform every other publicly available model on MultiPL-E. We release Code Llama under a permissive license that allows for both research and commercial use.