RerrFact: Reduced Evidence Retrieval Representations for Scientific Claim Verification

2022-02-05 · Ashish Rana, Deepanshu Khanna, Tirthankar Ghosal, Muskaan Singh, Harpreet Singh, Prashant Singh Rana

Exponential growth in digital information outlets and the race to publish has made scientific misinformation more prevalent than ever. However, the task to fact-verify a given scientific claim is not straightforward even for researchers. Scientific claim verification requires in-depth knowledge and great labor from domain experts to substantiate supporting and refuting evidence from credible scientific sources. The SciFact dataset and corresponding task provide a benchmarking leaderboard to the community to develop automatic scientific claim verification systems via extracting and assimilating relevant evidence rationales from source abstracts. In this work, we propose a modular approach that sequentially carries out binary classification for every prediction subtask as in the SciFact leaderboard. Our simple classifier-based approach uses reduced abstract representations to retrieve relevant abstracts. These are further used to train the relevant rationale-selection model. Finally, we carry out two-step stance predictions that first differentiate non-relevant rationales and then identify supporting or refuting rationales for a given claim. Experimentally, our system RerrFact with no fine-tuning, simple design, and a fraction of model parameters fairs competitively on the leaderboard against large-scale, modular, and joint modeling approaches. We make our codebase available at https://github.com/ashishrana160796/RerrFact.

📄 PDF Abstract BibTeX arXiv:2202.02646

Code (1)

ashishrana160796/rerrfact 공식 구현 pytorch

Tasks

Benchmarking Binary ClassificationClaim VerificationMisinformation Retrieval

Document-as-Image Representations Fall Short for Scientific Retrieval

2026-04-20 · Ghazal Khalighinejad, Raghuveer Thirukovalluru, Alexander H. Oh, Bhuwan Dhingra arxiv

Many recent document embedding models are trained on document-as-image representations, embedding rendered pages as images rather than the underlying source. Meanwhile, existing benchmarks for scientific document retriev…

Do We Need Bigger Models for Science? Task-Aware Retrieval with Small Language Models

2026-04-02 · Florian Kelber, Matthias Jobst, Yuni Susanti, Michael Färber arxiv

Scientific knowledge discovery increasingly relies on large language models, yet many existing scholarly assistants depend on proprietary systems with tens or hundreds of billions of parameters. Such reliance limits repr…

Question Answering

Agentic Hybrid RAG for Evidence-Grounded Muon Collider Analysis

2026-06-09 · Ruobing Jiang, Dawei Fu, Cheng Jiang, Tianyi Yang 외 arxiv

Muon collider research spans accelerator physics, detector instrumentation, and high-energy phenomenology, with relevant evidence scattered across a rapidly expanding and heterogeneous body of scientific literature. As h…

Semantic Retrieval Question Answering Answer Generation

AIRwaves at CheckThat! 2025: Retrieving Scientific Sources for Implicit Claims on Social Media with Dual Encoders and Neural Re-Ranking

2025-09-23 · Cem Ashbaugh, Leon Baumgärtner, Tim Gress, Nikita Sidorov 외 arxiv

Linking implicit scientific claims made on social media to their original publications is crucial for evidence-based fact-checking and scholarly discourse, yet it is hindered by lexical sparsity, very short queries, and …

VecTree-RAG: An Agentic Retrieval-Augmented Generation Framework Combining Vector and Tree Retrieval for Efficiency and Accuracy

2026-07-25 · Xinyan Zhong, Yuwei Shi, Yuqi Wei, Chen Shen 외 arxiv

Scientific question answering requires a retrieval system to solve two distinct problems: identifying which papers are relevant and locating the supporting evidence within those papers. Conventional retrieval-augmented g…