GenProve: Learning to Generate Text with Fine-Grained Provenance
Large language models (LLM) often hallucinate, and while adding citations is a common solution, it is frequently insufficient for accountability as users struggle to verify how a cited source supports a generated claim. Existing methods are typically coarse-grained and fail to distinguish between direct quotes and complex reasoning. In this paper, we introduce Generation-time Fine-grained Provenance, a task where models must generate fluent answers while simultaneously producing structured, sentence-level provenance triples. To enable this, we present ReFInE (Relation-aware Fine-grained Interpretability & Evidence), a dataset featuring expert verified annotations that distinguish between Quotation, Compression, and Inference. Building on ReFInE, we propose GenProve, a framework that combines Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO). By optimizing a composite reward for answer fidelity and provenance correctness, GenProve significantly outperforms 14 strong LLMs in joint evaluation. Crucially, our analysis uncovers a reasoning gap where models excel at surface-level quotation but struggle significantly with inference-based provenance, suggesting that verifiable reasoning remains a frontier challenge distinct from surface-level citation.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
TROVE: A Challenge for Fine-Grained Text Provenance via Source Sentence Tracing and Relationship Classification
LLMs have achieved remarkable fluency and coherence in text generation, yet their widespread adoption has raised concerns about content reliability and accountability. In high-stakes domains such as healthcare, law, and …
RetrievalSentenceSentence RetrievalText GenerationBileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature
Text watermarks for large language models (LLMs) have been commonly used to identify the origins of machine-generated content, which is promising for assessing liability when combating deepfake or harmful content. While …
Face SwappingWhat is Your Article Based On? Inferring Fine-grained Provenance
When evaluating an article and the claims it makes, a critical reader must be able to assess where the information presented comes from, and whether the various claims are mutually consistent and support the conclusion. …
ArticlesFact CheckingSentenceFacilitating the sharing of electrophysiology data analysis results through in-depth provenance capture
Scientific research demands reproducibility and transparency, particularly in data-intensive fields like electrophysiology. Electrophysiology data is typically analyzed using scripts that generate output files, including…
Transfer LearningSMA: Who Said That? Auditing Membership Leakage in Semi-Black-box RAG Controlling
Retrieval-Augmented Generation (RAG) and its Multimodal Retrieval-Augmented Generation (MRAG) significantly improve the knowledge coverage and contextual understanding of Large Language Models (LLMs) by introducing exter…
Image Retrieval