Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.03669 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911357804216320 |
|---|---|
| author | Chu, Bohao Wang, Qianli Damm, Hendrik Wang, Hui Muhabbek, Ula Livingstone, Elisabeth Friedrich, Christoph M. Fuhr, Norbert |
| author_facet | Chu, Bohao Wang, Qianli Damm, Hendrik Wang, Hui Muhabbek, Ula Livingstone, Elisabeth Friedrich, Christoph M. Fuhr, Norbert |
| contents | How can system-generated responses be efficiently verified, especially in the high-stakes biomedical domain? To address this challenge, we introduce eTracer, a plug-and-play framework that enables traceable text generation by grounding claims against contextual evidence. Through post-hoc grounding, each response claim is aligned with contextual evidence that either supports or contradicts it. Building on claim-level grounding results, eTracer not only enables users to precisely trace responses back to their contextual source but also quantifies response faithfulness, thereby enabling the verifiability and trustworthiness of generated responses. Experiments show that our claim-level grounding approach alleviates the limitations of conventional grounding methods in aligning generated statements with contextual sentence-level evidence, resulting in substantial improvements in overall grounding quality and user verification efficiency. The code and data are available at https://github.com/chubohao/eTracer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_03669 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | eTracer: Towards Traceable Text Generation via Claim-Level Grounding Chu, Bohao Wang, Qianli Damm, Hendrik Wang, Hui Muhabbek, Ula Livingstone, Elisabeth Friedrich, Christoph M. Fuhr, Norbert Computation and Language How can system-generated responses be efficiently verified, especially in the high-stakes biomedical domain? To address this challenge, we introduce eTracer, a plug-and-play framework that enables traceable text generation by grounding claims against contextual evidence. Through post-hoc grounding, each response claim is aligned with contextual evidence that either supports or contradicts it. Building on claim-level grounding results, eTracer not only enables users to precisely trace responses back to their contextual source but also quantifies response faithfulness, thereby enabling the verifiability and trustworthiness of generated responses. Experiments show that our claim-level grounding approach alleviates the limitations of conventional grounding methods in aligning generated statements with contextual sentence-level evidence, resulting in substantial improvements in overall grounding quality and user verification efficiency. The code and data are available at https://github.com/chubohao/eTracer. |
| title | eTracer: Towards Traceable Text Generation via Claim-Level Grounding |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2601.03669 |