Augmenting the Veracity and Explanations of Complex Fact Checking via Iterative Self-Revision with LLMs

• URL: http://arxiv.org/abs/2410.15135v1
• Date: Sat, 19 Oct 2024 15:25:19 GMT
• Title: Augmenting the Veracity and Explanations of Complex Fact Checking via Iterative Self-Revision with LLMs
• Authors: Xiaocheng Zhang, Xi Wang, Yifei Lu, Zhuangzhuang Ye, Jianing Wang, Mengjiao Bao, Peng Yan, Xiaohong Su,
• Abstract summary: We construct two complex fact-checking datasets in the Chinese scenarios: CHEF-EG and TrendFact. These datasets involve complex facts in areas such as health, politics, and society. We propose a unified framework called FactISR to perform mutual feedback between veracity and explanations.
• Score: 10.449165630417522
• License:
• Abstract: Explanation generation plays a more pivotal role than fact verification in producing interpretable results and facilitating comprehensive fact-checking, which has recently garnered considerable attention. However, previous studies on explanation generation has shown several limitations, such as being confined to English scenarios, involving overly complex inference processes, and not fully unleashing the potential of the mutual feedback between veracity labels and explanation texts. To address these issues, we construct two complex fact-checking datasets in the Chinese scenarios: CHEF-EG and TrendFact. These datasets involve complex facts in areas such as health, politics, and society, presenting significant challenges for fact verification methods. In response to these challenges, we propose a unified framework called FactISR (Augmenting Fact-Checking via Iterative Self-Revision) to perform mutual feedback between veracity and explanations by leveraging the capabilities of large language models(LLMs). FactISR uses a single model to address tasks such as fact verification and explanation generation. Its self-revision mechanism can further revision the consistency between veracity labels, explanation texts, and evidence, as well as eliminate irrelevant noise. We conducted extensive experiments with baselines and FactISR on the proposed datasets. The experimental results demonstrate the effectiveness of our method.

Related papers

• ZeFaV: Boosting Large Language Models for Zero-shot Fact Verification [2.6874004806796523]
  ZeFaV is a zero-shot based fact-checking verification framework to enhance the performance on fact verification task of large language models. We conducted empirical experiments to evaluate our approach on two multi-hop fact-checking datasets including HoVer and FEVEROUS.
  arXiv  Detail & Related papers  (2024-11-18T02:35:15Z)
• FactLens: Benchmarking Fine-Grained Fact Verification [6.814173254027381]
  We advocate for a shift toward fine-grained verification, where complex claims are broken down into smaller sub-claims for individual verification. We introduce FactLens, a benchmark for evaluating fine-grained fact verification, with metrics and automated evaluators of sub-claim quality. Our results show alignment between automated FactLens evaluators and human judgments, and we discuss the impact of sub-claim characteristics on the overall verification performance.
  arXiv  Detail & Related papers  (2024-11-08T21:26:57Z)
• Self-Distilled Disentangled Learning for Counterfactual Prediction [49.84163147971955]
  We propose the Self-Distilled Disentanglement framework, known as $SD2$. Grounded in information theory, it ensures theoretically sound independent disentangled representations without intricate mutual information estimator designs. Our experiments, conducted on both synthetic and real-world datasets, confirm the effectiveness of our approach.
  arXiv  Detail & Related papers  (2024-06-09T16:58:19Z)
• RU22Fact: Optimizing Evidence for Multilingual Explainable Fact-Checking on Russia-Ukraine Conflict [34.2739191920746]
  High-quality evidence plays a vital role in enhancing fact-checking systems. We propose a method based on a Large Language Model to automatically retrieve and summarize evidence from the Web. We construct RU22Fact, a novel explainable fact-checking dataset on the Russia-Ukraine conflict in 2022 of 16K samples.
  arXiv  Detail & Related papers  (2024-03-25T11:56:29Z)
• FENICE: Factuality Evaluation of summarization based on Natural language Inference and Claim Extraction [85.26780391682894]
  We propose Factuality Evaluation of summarization based on Natural language Inference and Claim Extraction (FENICE) 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.
  arXiv  Detail & Related papers  (2024-03-04T17:57:18Z)
• Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debate [75.10515686215177]
  Large Language Models (LLMs) excel in text generation, but their capability for producing faithful explanations in fact-checking remains underexamined. We propose the Multi-Agent Debate Refinement (MADR) framework, leveraging multiple LLMs as agents with diverse roles. MADR ensures that the final explanation undergoes rigorous validation, significantly reducing the likelihood of unfaithful elements and aligning closely with the provided evidence.
  arXiv  Detail & Related papers  (2024-02-12T04:32:33Z)
• How We Refute Claims: Automatic Fact-Checking through Flaw Identification and Explanation [4.376598435975689]
  This paper explores the novel task of flaw-oriented fact-checking, including aspect generation and flaw identification. We also introduce RefuteClaim, a new framework designed specifically for this task. Given the absence of an existing dataset, we present FlawCheck, a dataset created by extracting and transforming insights from expert reviews into relevant aspects and identified flaws.
  arXiv  Detail & Related papers  (2024-01-27T06:06:16Z)
• FactCHD: Benchmarking Fact-Conflicting Hallucination Detection [64.4610684475899]
  FactCHD is a benchmark designed for the detection of fact-conflicting hallucinations from LLMs. FactCHD features a diverse dataset that spans various factuality patterns, including vanilla, multi-hop, comparison, and set operation. We introduce Truth-Triangulator that synthesizes reflective considerations by tool-enhanced ChatGPT and LoRA-tuning based on Llama2.
  arXiv  Detail & Related papers  (2023-10-18T16:27:49Z)
• EX-FEVER: A Dataset for Multi-hop Explainable Fact Verification [22.785622371421876]
  We present a pioneering dataset for multi-hop explainable fact verification. With over 60,000 claims involving 2-hop and 3-hop reasoning, each is created by summarizing and modifying information from hyperlinked Wikipedia documents. We demonstrate a novel baseline system on our EX-FEVER dataset, showcasing document retrieval, explanation generation, and claim verification.
  arXiv  Detail & Related papers  (2023-10-15T06:46:15Z)
• Generating Fact Checking Explanations [52.879658637466605]
  A crucial piece of the puzzle that is still missing is to understand how to automate the most elaborate part of the process. This paper provides the first study of how these explanations can be generated automatically based on available claim context. Our results indicate that optimising both objectives at the same time, rather than training them separately, improves the performance of a fact checking system.
  arXiv  Detail & Related papers  (2020-04-13T05:23:25Z)
• Enhancing Factual Consistency of Abstractive Summarization [57.67609672082137]
  We propose a fact-aware summarization model FASum to extract and integrate factual relations into the summary generation process. We then design a factual corrector model FC to automatically correct factual errors from summaries generated by existing systems.
  arXiv  Detail & Related papers  (2020-03-19T07:36:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.