In recent years, Large Language Models (LLMs) have demonstrated an impressive ability to encode knowledge during pre-training on large text corpora. They can leverage this knowledge for downstream tasks like question answering (QA), even in complex areas involving health topics. Considering their high potential for facilitating clinical work in the future, understanding the quality of encoded medical knowledge and its recall in LLMs is an important step forward. In this study, we examine the capability of LLMs to exhibit medical knowledge recall by constructing a novel dataset derived from systematic reviews – studies synthesizing evidence-based answers for specific medical questions. Through experiments on the new MedREQAL dataset, comprising question-answer pairs extracted from rigorous systematic reviews, we assess six LLMs, such as GPT and Mixtral, analyzing their classification and generation performance. Our experimental insights into LLM performance on the novel biomedical QA dataset reveal the still challenging nature of this task.
论文检索
输入标题、作者或关键词，从 9,460 篇学术成果中精准定位
This paper investigates unsupervised multimodal domain adaptation for multimodal emotion recognition, which is a solution for data scarcity yet remains under studied. Due to the varying distribution discrepancies of different modalities between source and target domains, the primary challenge lies in how to balance the domain alignment across modalities to guarantee they are all well aligned. To achieve this, we first develop our model based on the information bottleneck theory to learn optimal representation for each modality independently. Then, we align the domains via matching the label distributions and the representations. In order to balance the representation alignment, we propose to minimize a surrogate of the alignment losses, which is equivalent to adaptively adjusting the weights of the modalities throughout training, thus achieving balanced domain alignment across modalities. Overall, the proposed approach features Adaptively modality-balanced domain adaptation, dubbed Amanda, for multimodal emotion recognition. Extensive empirical results on commonly used benchmark datasets demonstrate that Amanda significantly outperforms competing approaches. The code is available at https://github.com/sunjunaimer/Amanda.
Pre-trained Language Models (PLMs) have shown impressive results in various Natural Language Generation (NLG) tasks, such as powering chatbots and generating stories. However, an ethical concern arises due to their potential to produce verbatim copies of paragraphs from their training data. This is problematic as PLMs are trained on corpora constructed by human authors. As such, there is a pressing need for research to promote the generation of original content by these models. In this study, we introduce a unique “self-plagiarism” contrastive decoding strategy, aimed at boosting the originality of text produced by PLMs. Our method entails modifying prompts in LLMs to develop an amateur model and a professional model. Specifically, the amateur model is urged to plagiarize using three plagiarism templates we have designed, while the professional model maintains its standard language model status. This strategy employs prompts to stimulate the model’s capacity to identify non-original candidate token combinations and subsequently impose penalties. The application of this strategy is integrated prior to the model’s final layer, ensuring smooth integration with most existing PLMs (T5, GPT, LLaMA) without necessitating further adjustments. Implementing our strategy, we noted a significant decline in non-original sequences comprised of more than three words in the academic AASC dataset and the story-based ROCStories dataset. Source code and scripts will be released after the paper’s acceptance and publication.
Modern natural language processing (NLP) systems thrive when given access to large datasets. However, a large fraction of the world’s languages are not privy to such benefits due to sparse documentation and inadequate digital representation. This is especially true for Indian regional languages. As a first step towards expanding the reach of NLP technologies to extremely low-resource Indian languages, we present a new parallel part-of-speech (POS) evaluation dataset for Angika, Magahi, Bhojpuri and Hindi. Angika, Magahi, Bhojpuri, along with the more well-known Hindi, are all languages spoken in the Indian states of Bihar, Jharkhand and West Bengal. Ours is notably the first NLP resource, even for a shallow NLP task like POS-tagging, for Angika. We establish POS-tagging baselines using state-of-the-art multilingual pretrained language models (PLMs) finetuned on Hindi data, and show zero-shot evaluations on the other three languages. While all four languages use the same Devanagari script, pretrained tokenizers underperform in zero-shot on the three languages. We propose a simple look-back fix to address the tokenization challenge yielding F1-score improvements of up to 8% on Angika and show how it comes very close to an oracle setting when the underlying Hindi word is known (and can be accurately tokenized).
Despite outstanding performance in a variety of Natural Language Processing (NLP) tasks, recent studies have revealed that NLP models are vulnerable to adversarial attacks that slightly perturb the input to cause the models to misbehave. Several attacks can even compromise the model without requiring access to the model architecture or model parameters (i.e., a blackbox setting), and thus are detrimental to existing NLP applications. To perform these attacks, the adversary queries the victim model many times to determine the most important parts in an input text and transform. In this work, we propose a lightweight and attack-agnostic defense whose main goal is to perplex the process of generating an adversarial example in these query-based black-box attacks; that is to fool the textual fooler. This defense, named AdvFooler, works by randomizing the latent representation of the input at inference time. Different from existing defenses, AdvFooler does not necessitate additional computational overhead during training nor does it rely on assumptions about the potential adversarial perturbation set while having a negligible impact on the model’s accuracy. Our theoretical and empirical analyses highlight the significance of robustness resulting from confusing the adversary via randomizing the latent space, as well as the impact of randomization on clean accuracy. Finally, we empirically demonstrate near state-of-the-art robustness of AdvFooler against representative adversarial attacks on two benchmark datasets.
Understanding sentiment is arguably an advanced and important capability of AI agents in the physical world. In previous works, many efforts have been devoted to individual sentiment subtasks, without considering interrelated sentiment knowledge among these subtasks. Although some recent works model multiple sentiment subtasks in a unified manner, they merely simply combine these subtasks without deeply exploring the hierarchical relationships among subtasks. In this paper, we introduce GSA-7B, an open-source large language model specific to the sentiment domain. Specifically, we deeply explore the hierarchical relationships between sentiment subtasks, proposing progressive sentiment reasoning benchmark and progressive task instructions. Subsequently, we use Llama2-7B as the backbone model and propose parameter-efficient progressive tuning paradigm which is implemented by constructing chain of LoRA, resulting in the creation of GSA-7B. Experimental results show that GSA-7B as a unified model performs well across all datasets in the progressive sentiment reasoning benchmark. Additionally, under the few-shot setting, GSA-7B also exhibits good generalization ability for sentiment subtasks and datasets that were not encountered during its training phase.
Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models
PDF ↗Hallucinations in large language models (LLMs) refer to the phenomenon of LLMs producing responses that are coherent yet factually inaccurate. This issue undermines the effectiveness of LLMs in practical applications, necessitating research into detecting and mitigating hallucinations of LLMs. Previous studies have mainly concentrated on post-processing techniques for hallucination detection, which tend to be computationally intensive and limited in effectiveness due to their separation from the LLM’s inference process. To overcome these limitations, we introduce MIND, an unsupervised training framework that leverages the internal states of LLMs for real-time hallucination detection without requiring manual annotations. Additionally, we present HELM, a new benchmark for evaluating hallucination detection across multiple LLMs, featuring diverse LLM outputs and the internal states of LLMs during their inference process. Our experiments demonstrate that MIND outperforms existing state-of-the-art methods in hallucination detection.
Temporal knowledge graph reasoning has emerged as a crucial task for answering time-dependent questions within a knowledge graph (KG).Despite tremendous progress, the present research is impeded by the sparsity of a temporal KG and an over-reliance on simple single-relational reasoning patterns. To overcome these challenges, we introduce MulQuestions, a new temporal KG reasoning benchmark featuring over 200k entities and 960k questions designed to facilitate complex, multi-relational and multi-hop reasoning. Additionally, we propose a new model adept at conducting pattern-aware and time-sensitive reasoning across temporal KGs. The model’s efficacy is confirmed through rigorous evaluations, showcasing its effectiveness in sparse data conditions and adeptness at handling questions with long reasoning chains. We have made our benchmark and model publicly accessible at [https://anonymous].
Generalisation First, Memorisation Second? Memorisation Localisation for Natural Language Classification Tasks
PDF ↗Memorisation is a natural part of learning from real-world data: neural models pick up on atypical input-output combinations and store those training examples in their parameter space. That this happens is well-known, but how and where are questions that remain largely unanswered. Given a multi-layered neural model, where does memorisation occur in the millions of parameters?Related work reports conflicting findings: a dominant hypothesis based on image classification is that lower layers learn generalisable features and that deeper layers specialise and memorise. Work from NLP suggests this does not apply to language models, but has been mainly focused on memorisation of facts.We expand the scope of the localisation question to 12 natural language classification tasks and apply 4 memorisation localisation techniques.Our results indicate that memorisation is a gradual process rather than a localised one, establish that memorisation is task-dependent, and give nuance to the generalisation first, memorisation second hypothesis.
Word Sense Disambiguation (WSD) is the task of associating a word in a given context with its most suitable meaning among a set of possible candidates. While the task has recently witnessed renewed interest, with systems achieving performances above the estimated inter-annotator agreement, at the time of writing it still struggles to find downstream applications. We argue that one of the reasons behind this is the difficulty of applying WSD to plain text. Indeed, in the standard formulation, models work under the assumptions that a) all the spans to disambiguate have already been identified, and b) all the possible candidate senses of each span are provided, both of which are requirements that are far from trivial. In this work, we present a new task called Word Sense Linking (WSL) where, given an input text and a reference sense inventory, systems have to both identify which spans to disambiguate and then link them to their most suitable meaning.We put forward a transformer-based architecture for the task and thoroughly evaluate both its performance and those of state-of-the-art WSD systems scaled to WSL, iteratively relaxing the assumptions of WSD. We hope that our work will foster easier integration of lexical semantics into downstream applications.
As corporations rush to integrate large language models (LLMs) it is critical that they provide factually accurate information, that is robust to any presuppositions that a user may express. In this work, we introduce UPHILL, a dataset consisting of health-related queries with varying degrees of presuppositions. Using UPHILL, we evaluate the factual accuracy and consistency of InstructGPT, ChatGPT, GPT-4 and Bing Copilot models. We find that while model responses rarely contradict true health claims (posed as questions), all investigated models fail to challenge false claims. Alarmingly, responses from these models agree with 23-32% of the existing false claims, and 49-55% with novel fabricated claims. As we increase the extent of presupposition in input queries, responses from all models except Bing Copilot agree with the claim considerably more often, regardless of its veracity. Given the moderate factual accuracy, and the inability of models to challenge false assumptions, our work calls for a careful assessment of current LLMs for use in high-stakes scenarios.
In an ever-expanding world of domain-specific knowledge, the increasing complexity of consuming, and storing information necessitates the generation of summaries from large information repositories. However, every persona of a domain has different requirements of information and hence their summarization. For example, in the healthcare domain, a persona-based (such as Doctor, Nurse, Patient etc.) approach is imperative to deliver targeted medical information efficiently. Persona-based summarization of domain-specific information by humans is a high cognitive load task and is generally not preferred. The summaries generated by two different humans have high variability and do not scale in cost and subject matter expertise as domains and personas grow. Further, AI-generated summaries using generic Large Language Models (LLMs) may not necessarily offer satisfactory accuracy for different domains unless they have been specifically trained on domain-specific data and can also be very expensive to use in day-to-day operations. Our contribution in this paper is two-fold: 1) We present an approach to efficiently fine-tune a domain-specific small foundation LLM using a healthcare corpus and also show that we can effectively evaluate the summarization quality using AI-based critiquing. 2) We further show that AI-based critiquing has good concordance with Human-based critiquing of the summaries. Hence, such AI-based pipelines to generate domain-specific persona-based summaries can be easily scaled to other domains such as legal, enterprise documents, education etc. in a very efficient and cost-effective manner.
NUMCoT: Numerals and Units of Measurement in Chain-of-Thought Reasoning using Large Language Models
PDF ↗Numeral systems and units of measurement are two conjoined topics in activities of human beings and have mutual effects with the languages expressing them. Currently, the evaluation of Large Language Models (LLMs) often involves mathematical reasoning, yet little attention is given to how minor changes in numbers or units can drastically alter the complexity of problems and the performance of LLMs. In this paper, we scrutinize existing LLMs on processing of numerals and units of measurement by constructing datasets with perturbations. We first anatomize the reasoning of math word problems to different sub-procedures like numeral conversions from language to numbers and measurement conversions based on units. Then we further annotate math word problems from ancient Chinese arithmetic works which are challenging in numerals and units of measurement. Experiments on perturbed datasets demonstrate that LLMs still encounter difficulties in handling numeral and measurement conversions.
Data scarcity and the modality gap between the speech and text modalities are two major obstacles of end-to-end Speech Translation (ST) systems, thus hindering their performance. Prior work has attempted to mitigate these challenges by leveraging external MT data and optimizing distance metrics that bring closer the speech-text representations. However, achieving competitive results typically requires some ST data. For this reason, we introduce ZeroSwot, a method for zero-shot ST that bridges the modality gap without any paired ST data. Leveraging a novel CTC compression and Optimal Transport, we train a speech encoder using only ASR data, to align with the representation space of a massively multilingual MT model. The speech encoder seamlessly integrates with the MT model at inference, enabling direct translation from speech to text, across all languages supported by the MT model. Our experiments show that we can effectively close the modality gap without ST data, while our results on MuST-C and CoVoST demonstrate our method’s superiority over not only previous zero-shot models, but also supervised ones, achieving state-of-the-art results.
Large Language Models (LLMs) have demonstrated an impressive capability known as In-context Learning (ICL), which enables them to acquire knowledge from textual demonstrations without the need for parameter updates.However, many studies have highlighted that the model’s performance is sensitive to the choice of demonstrations, presenting a significant challenge for practical applications where we lack prior knowledge of user queries.Consequently, we need to construct an extensive demonstration pool and incorporate external databases to assist the model, leading to considerable time and financial costs.In light of this, some recent research has shifted focus towards zero-shot ICL, aiming to reduce the model’s reliance on external information by leveraging their inherent generative capabilities. Despite the effectiveness of these approaches, the content generated by the model may be unreliable, and the generation process is time-consuming.To address these issues, we propose Demonstration Augmentation for In-context Learning (DAIL), which employs the model’s previously predicted historical samples as demonstrations for subsequent ones.DAIL brings no additional inference cost and does not rely on the model’s generative capabilities.Our experiments reveal that DAIL can significantly improve the model’s performance over direct zero-shot inference and can even outperform few-shot ICL without any external information.
Dual-Stage Multi-Task Syntax-Oriented Pre-Training for Syntactically Controlled Paraphrase Generation
PDF ↗Syntactically Controlled Paraphrase Generation (SCPG), which aims at generating sentences having syntactic structures resembling given exemplars, is attracting more research efforts in recent years. We took an empirical survey on previous SCPG datasets and methods and found three tacitly approved while seldom mentioned intrinsic shortcomings/trade-offs in terms of data obtaining, task formulation, and pre-training strategies. As a mitigation to these shortcomings, we proposed a novel Dual-Stage Multi-Task (DSMT) pre-training scheme, involving a series of structure-oriented and syntax-oriented tasks, which, in our opinion, gives sequential text models the ability of com-prehending intrinsically non-sequential structures like Linearized Constituency Trees (LCTs), understanding the underlying syntactics, and even generating them by parsing sentences. We performed further pre-training of the popular T5 model on these novel tasks and fine-tuned the trained model on every possible variant of SCPG task in literature, finding that our models significantly outperformed (up to 10+ BLEU-4) previous state-of-the-art methods. Finally, we carried out ablation studies which demonstrated the effectiveness of our DSMT methods and emphasized on the SCPG performance gains compared to vanilla T5 models, especially on hard samples or under few-shot settings.
mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humans
PDF ↗It is very challenging to curate a dataset for language-specific knowledge and common sense in order to evaluate natural language understanding capabilities of language models. Due to the limitation in the availability of annotators, most current multilingual datasets are created through translation, which cannot evaluate such language-specific aspects. Therefore, we propose Multilingual CommonsenseQA (mCSQA) based on the construction process of CSQA but leveraging language models for a more efficient construction, e.g., by asking LM to generate questions/answers, refine answers and verify QAs followed by reduced human efforts for verification. Constructed dataset is a benchmark for cross-lingual language-transfer capabilities of multilingual LMs, and experimental results showed high language-transfer capabilities for questions that LMs could easily solve, but lower transfer capabilities for questions requiring deep knowledge or commonsense. This highlights the necessity of language-specific datasets for evaluation and training. Finally, our method demonstrated that multilingual LMs could create QA including language-specific knowledge, significantly reducing the dataset creation cost compared to manual creation. The datasets are available at https://huggingface.co/datasets/yusuke1997/mCSQA.
Looking Right is Sometimes Right: Investigating the Capabilities of Decoder-only LLMs for Sequence Labeling
PDF ↗Pre-trained language models based on masked language modeling (MLM) excel in natural language understanding (NLU) tasks. While fine-tuned MLM-based encoders consistently outperform causal language modeling decoders of comparable size, recent decoder-only large language models (LLMs) perform on par with smaller MLM-based encoders. Although their performance improves with scale, LLMs fall short of achieving state-of-the-art results in information extraction (IE) tasks, many of which are formulated as sequence labeling (SL). We hypothesize that LLMs’ poor SL performance stems from causal masking, which prevents the model from attending to tokens on the right of the current token. Yet, how exactly and to what extent LLMs’ performance on SL can be improved remains unclear. We explore techniques for improving the SL performance of open LLMs on IE tasks by applying layer-wise removal of the causal mask (CM) during LLM fine-tuning. This approach yields performance gains competitive with state-of-the-art SL models, matching or outperforming the results of CM removal from all blocks. Our findings hold for diverse SL tasks, demonstrating that open LLMs with layer-dependent CM removal outperform strong MLM-based encoders and even instruction-tuned LLMs.
Recently, the self-consistency decoding strategy has shown the ability to improve performance for complex reasoning tasks with large language models (LLMs). However, the costs may be high because the sampling process of the strategy generates some low-probability text, resulting in low-quality reasoning paths. As a consequence, it requires a relatively large sampling number to obtain good aggregation performance. In this paper, we propose an alternative strategy, self-para-consistency. It first generates multiple paraphrases for each test question, then generates reasoning paths for the original and all the paraphrased questions based on greedy decoding, and finally selects the most consistent answer. Since all the candidate paths have relatively high probabilities, the sampling number could be much smaller than the self-consistency strategy. Extensive experiments on complex reasoning datasets demonstrate the effectiveness of our method in reducing the sampling number.
FENICE: Factuality Evaluation of summarization based on Natural language Inference and Claim Extraction
PDF ↗Recent advancements in text summarization, particularly with the advent of Large Language Models (LLMs), have shown remarkable performance. However, a notable challenge persists as a substantial number of automatically-generated summaries exhibit factual inconsistencies, such as hallucinations. In response to this issue, various approaches for the evaluation of consistency for summarization have emerged. Yet, these newly-introduced metrics face several limitations, including lack of interpretability, focus on short document summaries (e.g., news articles), and computational impracticality, especially for LLM-based metrics. To address these shortcomings, we propose Factuality Evaluation of summarization based on Natural language Inference and Claim Extraction (FENICE), a more interpretable and efficient factuality-oriented metric. FENICE leverages an NLI-based alignment between information in the source document and a set of atomic facts, referred to as claims, extracted from the summary. Our metric sets a new state of the art on AGGREFACT, the de-facto benchmark for factuality evaluation. Moreover, we extend our evaluation to a more challenging setting by conducting a human annotation process of long-form summarization. In the hope of fostering research in summarization factuality evaluation, we release the code of our metric and our factuality annotations of long-form summarization at https://github.com/Babelscape/FENICE.