paper-with-me

Papers

SEEK: Semantic Evidence Extraction via Adaptive ChunKing for Multilingual Fact-Checking

2026-05-26 · Gaurav Kumar, Babu Kumar, Ayush Garg, Aditya Kishore, Jasabanta Patro arxiv

Multilingual fact verification requires evidence that is both relevant and sufficiently complete for reliable factuality prediction. However, existing systems often rely on search snippets, sentence-level evidence, or locally segmented passages, which can miss decisive context and produce fragmented evidence. To overcome these limitations, we propose SEEK, a Semantic Evidence Extraction with an adaptive chunKing framework that constructs coherent evidence chunks from full fact-checking articles by identifying semantic topic transitions and preserving local verification context. The constructed chunks are encoded using a multilingual encoder and then multilingual LLMs are finetuned using LoRA adapter for veracity prediction. Experiments on X-FACT and RU22Fact show that SEEK improves macro-f1 by up to 10% over semantic chunking, 19% over sentence chunking, and 20% over search-snippet baselines. Evidence completeness and significance analyses further show that SEEK preserves richer verification context and enables more reliable multilingual fact-checking.

📄 PDF Abstract BibTeX arXiv:2605.26755

Code (0)

등록된 구현이 없습니다.

Tasks

Fact Verification

Similar Papers 제목 키워드 기반

Is Semantic Chunking Worth the Computational Cost?

2024-10-16 · Renyi Qu, Ruixuan Tu, Forrest Bao

Recent advances in Retrieval-Augmented Generation (RAG) systems have popularized semantic chunking, which aims to improve retrieval performance by dividing documents into semantically coherent segments. Despite its growi…

Answer GenerationChunkingRAGRetrieval+1

SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation

2024-10-15 · Xinping Zhao, Dongfang Li, Yan Zhong, Boren Hu 외

Recent studies in Retrieval-Augmented Generation (RAG) have investigated extracting evidence from retrieved passages to reduce computational costs and enhance the final RAG performance, yet it remains challenging. Existi…

ChunkingRAGRetrievalRetrieval-augmented Generation+1

Query-Adaptive Semantic Chunking for Retrieval-Augmented Generation: A Dynamic Strategy with Contextual Window Expansion

2026-04-29 · Mudit Rastogi arxiv

Retrieval-Augmented Generation (RAG) systems depend critically on document chunking quality for retrieving relevant context. Fixed chunking segments documents into uniform units irrespective of semantics or user intent, …

Grounding Language Model with Chunking-Free In-Context Retrieval

2024-02-15 · Hongjin Qian, Zheng Liu, Kelong Mao, Yujia Zhou 외

This paper presents a novel Chunking-Free In-Context (CFIC) retrieval approach, specifically tailored for Retrieval-Augmented Generation (RAG) systems. Traditional RAG systems often struggle with grounding responses usin…

ChunkingLanguage ModelingLanguage ModellingRAG+3

FlexStructRAG: Flexible Structure-Aware Multi-Granular Relational Retrieval for RAG

2026-02-01 · Mengzhu Chen, Haodong Yang, Jia Cai, Xiaolin Huang arxiv

Retrieval-Augmented Generation (RAG) systems critically depend on how external knowledge is segmented, structured, and retrieved. Most existing approaches either retrieve fixed-length text chunks, which fragments discour…