FineRef: Fine-Grained Error Reflection and Correction for Long-Form Generation with Citations

• URL: http://arxiv.org/abs/2602.18437v1
• Date: Tue, 18 Nov 2025 09:35:12 GMT
• Title: FineRef: Fine-Grained Error Reflection and Correction for Long-Form Generation with Citations
• Authors: Yixing Peng, Licheng Zhang, Shancheng Fang, Yi Liu, Peijian Gu, Quan Wang,
• Abstract summary: FineRef teaches the model to self-identify and correct two key citation errors, mismatch and irrelevance, on a per-citation basis.<n>FineRef significantly improves both citation performance and answer accuracy.<n>Our 7B model outperforms GPT-4 by up to 18% in Citation F1 and 4% in EM Recall.
• Score: 30.28908306106096
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generating with citations is crucial for trustworthy Large Language Models (LLMs), yet even advanced LLMs often produce mismatched or irrelevant citations. Existing methods over-optimize citation fidelity while overlooking relevance to the user query, which degrades answer quality and robustness in real-world settings with noisy or irrelevant retrieved content. Moreover, the prevailing single-pass paradigm struggles to deliver optimal answers in long-form generation that requiring multiple citations. To address these limitations, we propose FineRef, a framework based on Fine-grained error Reflection, which explicitly teaches the model to self-identify and correct two key citation errors, mismatch and irrelevance, on a per-citation basis. FineRef follows a two-stage training strategy. The first stage instills an "attempt-reflect-correct" behavioral pattern via supervised fine-tuning, using fine-grained and controllable reflection data constructed by specialized lightweight models. An online self-reflective bootstrapping strategy is designed to improve generalization by iteratively enriching training data with verified, self-improving examples. To further enhance the self-reflection and correction capability, the second stage applies process-level reinforcement learning with a multi-dimensional reward scheme that promotes reflection accuracy, answer quality, and correction gain. Experiments on the ALCE benchmark demonstrate that FineRef significantly improves both citation performance and answer accuracy. Our 7B model outperforms GPT-4 by up to 18% in Citation F1 and 4% in EM Recall, while also surpassing the state-of-the-art model across key evaluation metrics. FineRef also exhibits strong generalization and robustness in domain transfer settings and noisy retrieval scenarios.

Related papers

• OCR-Agent: Agentic OCR with Capability and Memory Reflection [5.8505408398110434]
  Large Vision-Language Models (VLMs) have demonstrated significant potential on complex visual understanding tasks.<n>We propose a novel iterative self-correction framework that endows models with two key capabilities: Capability Reflection and Memory Reflection.<n> Experiments on the challenging OCRBench v2 benchmark show that OCR-Agent outperforms the current open-source SOTA model InternVL3-8B by +2.0 on English and +1.2 on Chinese subsets.
  arXiv  Detail & Related papers  (2026-02-24T16:10:27Z)
• Trust but Verify: Adaptive Conditioning for Reference-Based Diffusion Super-Resolution via Implicit Reference Correlation Modeling [42.10910149675583]
  Real-world degradations make correspondences between low-quality (LQ) inputs and reference (Ref) images unreliable.<n>We propose Ada-RefSR, a single-step diffusion framework guided by a "Trust but verify" principle.<n>Experiments on multiple datasets demonstrate that Ada-RefSR achieves a strong balance of fidelity, naturalness, and efficiency.
  arXiv  Detail & Related papers  (2026-02-02T09:34:57Z)
• PrefixNLI: Detecting Factual Inconsistencies as Soon as They Arise [60.63315470285562]
  MiniTruePrefixes is a novel specialized model that better detects factual inconsistencies over text prefixes.<n>We show that integrating MiniTruePrefixes into a controlled decoding framework substantially improves factual consistency in abstractive summarization.
  arXiv  Detail & Related papers  (2025-11-03T09:07:44Z)
• VeriCite: Towards Reliable Citations in Retrieval-Augmented Generation via Rigorous Verification [107.75781898355562]
  We introduce a novel framework, called VeriCite, designed to rigorously validate supporting evidence and enhance answer attribution.<n>We conduct experiments across five open-source LLMs and four datasets, demonstrating that VeriCite can significantly improve citation quality while maintaining the correctness of the answers.
  arXiv  Detail & Related papers  (2025-10-13T13:38:54Z)
• Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers [90.50039419576807]
  Reinforcement Learning with Verifiable Rewards (RLVR) trains policies against automated verifiers to avoid costly human labeling.<n>To reduce vulnerability to verifier hacking, many RLVR systems collapse rewards to binary $0,1$ during training.<n>This choice carries a cost: it introduces textitfalse negatives (rejecting correct answers, FNs) and textitfalse positives (accepting incorrect ones, FPs)
  arXiv  Detail & Related papers  (2025-10-01T13:56:44Z)
• CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward [50.97588334916863]
  We develop CompassVerifier, an accurate and robust lightweight verifier model for evaluation and outcome reward.<n>It demonstrates multi-domain competency spanning math, knowledge, and diverse reasoning tasks, with the capability to process various answer types.<n>We introduce VerifierBench benchmark comprising model outputs collected from multiple data sources, augmented through manual analysis of metaerror patterns to enhance CompassVerifier.
  arXiv  Detail & Related papers  (2025-08-05T17:55:24Z)
• RefCritic: Training Long Chain-of-Thought Critic Models with Refinement Feedback [57.967762383794806]
  RefCritic is a long-chain-of-thought critic module based on reinforcement learning with dual rule-based rewards.<n>We evaluate RefCritic on Qwen2.5-14B-Instruct and DeepSeek-R1-Distill-Qwen-14B across five benchmarks.
  arXiv  Detail & Related papers  (2025-07-20T16:19:51Z)
• Lessons from Training Grounded LLMs with Verifiable Rewards [24.35637263339965]
  Reinforcement learning and internal reasoning can enhance grounding in large language models.<n>We show that reasoning-augmented models significantly outperform instruction-only variants.<n>A two-stage training setup, first optimizing answer and citation behavior and then refusal, further improves grounding.
  arXiv  Detail & Related papers  (2025-06-18T14:58:13Z)
• On the Capacity of Citation Generation by Large Language Models [38.47160164251295]
  Retrieval-augmented generation (RAG) appears as a promising method to alleviate the "hallucination" problem in large language models (LLMs)
  arXiv  Detail & Related papers  (2024-10-15T03:04:26Z)
• Think-then-Act: A Dual-Angle Evaluated Retrieval-Augmented Generation [3.2134014920850364]
  Large language models (LLMs) often face challenges such as temporal misalignment and generating hallucinatory content. We propose a dual-angle evaluated retrieval-augmented generation framework textitThink-then-Act'
  arXiv  Detail & Related papers  (2024-06-18T20:51:34Z)
• Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection [74.51523859064802]
  We introduce a new framework called Self-Reflective Retrieval-Augmented Generation (Self-RAG) Self-RAG enhances an LM's quality and factuality through retrieval and self-reflection. It significantly outperforms state-of-the-art LLMs and retrieval-augmented models on a diverse set of tasks.
  arXiv  Detail & Related papers  (2023-10-17T18:18:32Z)
• Towards Reliable and Fluent Large Language Models: Incorporating Feedback Learning Loops in QA Systems [10.58737969057445]
  We build a dataset to train a critic model capable of evaluating the citation, correctness, and fluency of responses generated by large language models. We propose an automated feedback mechanism that leverages the critic model to offer real-time feedback on heterogeneous aspects of generated text. Experimental results demonstrate the efficacy of our approach, including a 4% precision increase in citation and an approximately 8% enhancement in the MAUVE metric for fluency.
  arXiv  Detail & Related papers  (2023-09-08T09:39:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.