论文检索

Guiyang Hou, Yongliang Shen, Weiming Lu

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.

Weihang Su, Changyue Wang, Qingyao Ai, Yiran Hu, Zhijing Wu, Yujia Zhou, Yiqun Liu

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.

Jian Liu, Zihe Liu, Xueqiang Lyu, Peng Jin, Jinan Xu

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].

Verna Dankers, Ivan Titov

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.

Andrei Stefan Bejgu, Edoardo Barba, Luigi Procopio, Alberte Fernández-Castro, Roberto Navigli

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.

Navreet Kaur, Monojit Choudhury, Danish Pruthi

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.

Ankan Mullick, Sombit Bose, Rounak Saha, Ayan Bhowmick, Pawan Goyal, Niloy Ganguly, Prasenjit Dey, Ravi Kokku

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.

Ancheng Xu, Minghuan Tan, Lei Wang, Min Yang, Ruifeng Xu

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.

Ioannis Tsiamas, Gerard I. Gállego, José A. R. Fonollosa, Marta R. Costa-jussà

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.

Yi Su, Yunpeng Tai, Yixin Ji, Juntao Li, Yan Bowen, Min Zhang

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.

Hongxu Liu, Xiaojie Wang, Jiashen Sun, Ke Zeng, Wan Guanglu

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.

Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe

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.

David Dukić, Jan Šnajder

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.

Wenqing Chen, Weicheng Wang, Zhixuan Chu, Kui Ren, Zibin Zheng, Zhichao Lu

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.

Alessandro Scirè, Karim Ghonim, Roberto Navigli

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.

Jinggui Liang, Lizi Liao, Hao Fei, Jing Jiang

In Conversational Intent Discovery (CID), Small Language Models (SLMs) struggle with overfitting to familiar intents and fail to label newly discovered ones. This issue stems from their limited grasp of semantic nuances and their intrinsically discriminative framework. Therefore, we propose Synergizing Large Language Models (LLMs) with pre-trained SLMs for CID (SynCID). It harnesses the profound semantic comprehension of LLMs alongside the operational agility of SLMs. By utilizing LLMs to refine both utterances and existing intent labels, SynCID significantly enhances the semantic depth, subsequently realigning these enriched descriptors within the SLMs’ feature space to correct cluster distortion and promote robust learning of representations. A key advantage is its capacity for the early identification of new intents, a critical aspect for deploying conversational agents successfully. Additionally, SynCID leverages the in-context learning strengths of LLMs to generate labels for new intents. Thorough evaluations across a wide array of datasets have demonstrated its superior performance over traditional CID methods.

Riccardo Orlando, Pere-Lluís Huguet Cabot, Edoardo Barba, Roberto Navigli

Entity Linking (EL) and Relation Extraction (RE) are fundamental tasks in Natural Language Processing, serving as critical components in a wide range of applications. In this paper, we propose ReLiK, a Retriever-Reader architecture for both EL and RE, where, given an input text, the Retriever module undertakes the identification of candidate entities or relations that could potentially appear within the text. Subsequently, the Reader module is tasked to discern the pertinent retrieved entities or relations and establish their alignment with the corresponding textual spans. Notably, we put forward an innovative input representation that incorporates the candidate entities or relations alongside the text, making it possible to link entities or extract relations in a single forward pass and to fully leverage pre-trained language models contextualization capabilities, in contrast with previous Retriever-Reader-based methods, which require a forward pass for each candidate. Our formulation of EL and RE achieves state-of-the-art performance in both in-domain and out-of-domain benchmarks while using academic budget training and with up to 40x inference speed compared to competitors. Finally, we show how our architecture can be used seamlessly for Information Extraction (cIE), i.e. EL + RE, and setting a new state of the art by employing a shared Reader that simultaneously extracts entities and relations.

Lei Huang, Xiaocheng Feng, Weitao Ma, Yuxuan Gu, Weihong Zhong, Xiachong Feng, Weijiang Yu, Weihua Peng, Duyu Tang, Dandan Tu 等

Despite the impressive performance on information-seeking tasks, large language models (LLMs) still struggle with hallucinations. Attributed LLMs, which augment generated text with in-line citations, demonstrate potential in mitigating hallucinations and improving verifiability. However, current approaches suffer from suboptimal citation quality due to their reliance on in-context learning. Furthermore, the practice of merely citing document identifiers complicates the process for users to pinpoint specific supporting evidence. In this work, we introduce FRONT, a training framework that teaches LLMs to generate Fine-grained grounded citations. By initially grounding fine-grained supporting quotes, which then guide the generation process, these quotes not only provide supervision signals to improve citation quality but also serve as fine-grained attributions. Experiments on the ALCE benchmark demonstrate the efficacy of FRONT in generating superior grounded responses and highly supportive citations. With LLaMA-2-7B, the framework significantly outperforms all the baselines, achieving an average of 14.21% improvement in citation quality across all datasets, even surpassing ChatGPT.

Chaoran Zhang, Lixin Zou, Dan Luo, Xiangyang Luo, Zihao Li, Min Tang, Chenliang Li

该来源暂未提供摘要。

Abelardo Carlos Martinez Lorenzo, Pere-Lluís Huguet Cabot, Karim Ghonim, Lu Xu, Hee-Soo Choi, Alberte Fernández-Castro, Roberto Navigli

Data scarcity is a prevalent challenge in the era of Large Language Models (LLMs). The insatiable hunger of LLMs for large corpora becomes even more pronounced when dealing with non-English and low-resource languages. The issue is particularly exacerbated in Semantic Parsing (SP), i.e. the task of converting text into a formal representation. The complexity of semantic formalisms makes training human annotators and subsequent data annotation unfeasible on a large scale, especially across languages. To mitigate this, we first introduce the Multilingual Semantic Layer (MSL), a conceptual evolution of previous formalisms, which decouples from disambiguation and external inventories and simplifies the task. MSL provides the necessary tools to encode the meaning across languages, paving the way for developing a high-quality semantic parsing dataset across different languages in a semi-automatic strategy. Subsequently, we manually refine a portion of this dataset and fine-tune GPT-3.5 to propagate these refinements across the dataset. Then, we manually annotate 1,100 sentences in eleven languages, including low-resource ones. Finally, we assess our dataset’s quality, showcasing the performance gap reduction across languages in Semantic Parsing.