eTracer: Towards Traceable Text Generation via Claim-Level Grounding

2026-01-07

arXiv.org

AI Summary

This work addresses the challenge of efficiently verifying the factual accuracy and traceability of system-generated text in high-stakes domains such as biomedicine. To this end, the authors propose eTracer, a novel framework that introduces claim-level fine-grained provenance tracing, overcoming the limitations of conventional sentence-level alignment. By aligning each individual claim with its contextual evidence, eTracer enables precise溯源 and quantitative faithfulness assessment. The framework is designed for plug-and-play integration and jointly supports evidence alignment, entailment/contradiction classification, and credibility scoring. Experimental results demonstrate that eTracer significantly enhances provenance quality and user verification efficiency, thereby improving the trustworthiness of generated content in biomedical and other critical applications.

Technology Category

• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Knowledge Representation and Reasoning: Reasoning with Beliefs

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity
• Security and Privacy: Data transparency and provenance

Abstract

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.

Problem

• traceable text generation
• claim-level grounding
• response verification
• faithfulness
• biomedical domain

Innovation

• claim-level grounding
• traceable text generation
• post-hoc verification
• faithfulness quantification
• contextual evidence alignment