| Challenge: | Existing systems often exhibit unverifiable attributions, shallow evidence mapping, and hallucinated citations. |
| Approach: | They propose a claim verification system that provides source-level accountability and evidence traceability. |
| Outcome: | SciTrue outperforms RAG-based baselines in summary traceability, attribution accuracy, and context alignment in a human evaluation of 300 attributions. |
Similar Papers
Claim Verification in the Age of Large Language Models: A Survey (2026.acl-srw)
Copied to clipboard
| Challenge: | Recent election cycles have seen a large number of false information spread across social media and news platforms. |
| Approach: | They propose a framework for automated claim verification using Large Language Models and Retrieval Augmented Generation. |
| Outcome: | The proposed frameworks are based on large-scale models and new methods such as Retrieval Augmented Generation (RAG). |
Fact or Fiction: Verifying Scientific Claims (2020.emnlp-main)
Copied to clipboard
David Wadden, Shanchuan Lin, Kyle Lo, Lucy Lu Wang, Madeleine van Zuylen, Arman Cohan, Hannaneh Hajishirzi
| Challenge: | SciFact is a dataset of 1.4K expert-written scientific claims paired with evidence-containing abstracts annotated with labels and rationales. |
| Approach: | They construct a dataset of 1.4K scientific claims paired with evidence-containing abstracts annotated with labels and rationales to test their system. |
| Outcome: | The proposed system can verify claims related to COVID-19 by identifying evidence from the CORD-19 corpus. |
SciFact-Open: Towards open-domain scientific claim verification (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Current scientific claim verification systems can achieve very strong performance on limited contexts, in some cases approaching human agreement. |
| Approach: | They propose to pool and annotate top predictions from four state-of-the-art scientific claim verification models to evaluate their performance against large corpora. |
| Outcome: | The proposed system performs well on a corpus of 500K scientific abstracts. |
Pushing the Frontiers of Scientific Fact-Checking: The SCINLP Dataset (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly being used to understand how scientific research evolves, drawing growing interest from the research community. |
| Approach: | They propose a scientific fact-checking dataset, SCINLP, tailored to the NLP domain that verifies the veracity of scientific research questions across varying rationale contexts. |
| Outcome: | The proposed framework examines scientific claims and research focus from a curated collection of influential and reputable NLP papers published between 2000 and 2024. |
Towards Effective Extraction and Evaluation of Factual Claims (2025.acl-long)
Copied to clipboard
| Challenge: | Lack of a standardized evaluation framework impedes assessment and comparison of claim extraction methods. |
| Approach: | They propose a framework for evaluating claim extraction in the context of fact-checking . they also introduce Claimify, an LLM-based claim extraction method . |
| Outcome: | The proposed evaluation framework outperforms existing methods in the evaluation of claim extraction methods. |
Comparing Knowledge Sources for Open-Domain Scientific Claim Verification (2024.eacl-long)
Copied to clipboard
| Challenge: | Existing systems for fact-checking scientific claims assume that the documents containing the evidence are already provided and annotated or contained in a limited corpus. |
| Approach: | They perform an array of experiments to test the performance of open-domain claim verification systems on four datasets of biomedical and health claims in different settings. |
| Outcome: | The proposed system performs better with biomedical and health claims, while Wikipedia is more suited for everyday health concerns. |
FactLens: Benchmarking Fine-Grained Fact Verification (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown impressive capability in language generation and understanding, but their tendency to hallucinate and produce factually incorrect information remains a key limitation. |
| Approach: | They propose a benchmark to evaluate fine-grained fact verification where claims are broken down into smaller sub-claims for individual verification. |
| Outcome: | The proposed model enables more precise identification of inaccuracies, improved transparency, and reduced ambiguity in evidence retrieval. |
Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing claims verification models rely on annotated data, which is expensive to create at a large scale. |
| Approach: | They propose a model that can verify complex claims without annotated data . they leverage the in-context learning ability of Large Language Models to translate a claim into a First-Order-Logic clause . |
| Outcome: | The proposed model outperforms baseline models on three datasets . it performs well on the datasets, and the results are published online. |
SciClaims: An End-to-End Generative System for Biomedical Claim Analysis (2025.emnlp-demos)
Copied to clipboard
| Challenge: | SciClaims is an interactive web-based system for scientific claim analysis in the biomedical domain. |
| Approach: | They present SciClaims, an interactive web-based system for scientific claim analysis in the biomedical domain. |
| Outcome: | The system extracts factual claims from scientific texts and retrieves evidence from PubMed . it also verifies the validity of each claim using large language models . the system is optimized to run efficiently on a single GPU and is publicly available . |
A Systematic Survey of Claim Verification: Corpora, Systems, and Case Studies (2025.findings-emnlp)
Copied to clipboard
| Challenge: | This survey analyses 198 studies published between January 2022 and March 2025 . |
| Approach: | This survey synthesizes recent advances in CV corpus creation and system design. |
| Outcome: | The results of this study are synthesized from 198 studies published between January 2022 and March 2025. |