eTracer: Towards Traceable Text Generation via Claim-Level Grounding
This addresses the need for verifiable and trustworthy AI-generated text, particularly in critical applications such as biomedicine, though it appears incremental as it builds on existing grounding methods.
The paper tackles the problem of verifying system-generated responses in high-stakes domains like biomedicine by introducing eTracer, a plug-and-play framework for traceable text generation via claim-level grounding, which results in substantial improvements in grounding quality and user verification efficiency.
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.