# GenProve: Learning to Generate Text with Fine-Grained Provenance

arXiv: https://arxiv.org/abs/2601.04932 · HTML: https://mlsanity.com/paper/2601.04932/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 30 references that are in the map.
- First posted on arXiv 8 Jan 2026.

## Builds on (most cited first, 21 of 21)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [Baichuan 2: Open Large-scale Language Models](https://mlsanity.com/paper/2309.10305/) (2023)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance](https://mlsanity.com/paper/1909.02622/) (2019)
- [Attribute First, then Generate: Locally-attributable Grounded Text Generation](https://mlsanity.com/paper/2403.17104/) (2024)
- [GERE: Generative Evidence Retrieval for Fact Verification](https://mlsanity.com/paper/2204.05511/) (2022)
- [Citation-Enhanced Generation for LLM-based Chatbots](https://mlsanity.com/paper/2402.16063/) (2024)
- [Improving Attributed Text Generation of Large Language Models via Preference Learning](https://mlsanity.com/paper/2403.18381/) (2024)
- [On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook](https://mlsanity.com/paper/2307.16680/) (2023)
- [Verifiable Generation with Subsentence-Level Fine-Grained Citations](https://mlsanity.com/paper/2406.06125/) (2024)
- [Learning to Generate Answers with Citations via Factual Consistency Models](https://mlsanity.com/paper/2406.13124/) (2024)
- [CaLM: Contrasting Large and Small Language Models to Verify Grounded Generation](https://mlsanity.com/paper/2406.05365/) (2024)
- [VeriCite: Towards Reliable Citations in Retrieval-Augmented Generation via Rigorous Verification](https://mlsanity.com/paper/2510.11394/) (2025)
- [MIRAGE: Scaling Test-Time Inference with Parallel Graph-Retrieval-Augmented Reasoning Chains](https://mlsanity.com/paper/2508.18260/) (2025)
- [Traceable Text: Deepening Reading of AI-Generated Summaries with Phrase-Level Provenance Links](https://mlsanity.com/paper/2409.13099/) (2024)
- [TROVE: A Challenge for Fine-Grained Text Provenance via Source Sentence Tracing and Relationship Classification](https://mlsanity.com/paper/2503.15289/) (2025)
- [SCIRGC: Multi-Granularity Citation Recommendation and Citation Sentence Preference Alignment](https://mlsanity.com/paper/2505.20103/) (2025)

## Built on by (most cited first, 2 of 2)

- [TRACER: Verifiable Generative Provenance for Multimodal Tool-Using Agents](https://mlsanity.com/paper/2605.09934/) (2026)
- [Actions with Receipts: Jointly Binding Claims, Evidence, and Execution for Replayable Tool-Agent Auditing](https://mlsanity.com/paper/2610.00327/) (2026)

## Abstract (arXiv)

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.