Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.26755 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911725296549888 |
|---|---|
| author | Kumar, Babu Kumar, Gaurav Garg, Ayush Kishore, Aditya Patro, Jasabanta |
| author_facet | Kumar, Babu Kumar, Gaurav Garg, Ayush Kishore, Aditya Patro, Jasabanta |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_26755 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SEEK: Semantic Evidence Extraction via Adaptive ChunKing for Multilingual Fact-Checking Kumar, Babu Kumar, Gaurav Garg, Ayush Kishore, Aditya Patro, Jasabanta Computation and Language 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. |
| title | SEEK: Semantic Evidence Extraction via Adaptive ChunKing for Multilingual Fact-Checking |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2605.26755 |