mlsanityData to 14 Oct 2026

Reinforcement Retrieval Leveraging Fine-grained Feedback for Fact Checking News Claims with Black-Box LLM

arXiv 2404.17283 ↗First posted 26 Apr 2024cs.CLcited by 15

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

Retrieval-augmented language models have exhibited promising performance across various areas of natural language processing (NLP), including fact-critical tasks. However, due to the black-box nature of advanced large language models (LLMs) and the non-retrieval-oriented supervision signal of specific tasks, the training of retrieval model faces significant challenges under the setting of black-box LLM. We propose an approach leveraging Fine-grained Feedback with Reinforcement Retrieval (FFRR) to enhance fact-checking on news claims by using black-box LLM. FFRR adopts a two-level strategy to gather fine-grained feedback from the LLM, which serves as a reward for optimizing the retrieval policy, by rating the retrieved documents based on the non-retrieval ground truth of the task. We evaluate our model on two public datasets for real-world news claim verification, and the results demonstrate that FFRR achieves significant improvements over strong LLM-enabled and non-LLM baselines.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 49 of its 60 references that are in the map. First posted on arXiv 26 Apr 2024.

Builds on

49 of 60 references.

References · 49

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  6. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  7. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  8. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  9. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  10. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  11. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  12. 2017Billion-scale similarity search with GPUscited by 2,497
37 more
  1. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  2. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  3. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,653
  4. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
  5. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  6. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  7. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 894
  8. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  9. 2017Non-Autoregressive Neural Machine Translationcited by 463
  10. 2023Fine-Grained Human Feedback Gives Better Rewards for Language Model Trainingcited by 401
  11. 2017"Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detectioncited by 363
  12. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 353
  13. 2022Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoningcited by 350
  14. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 318
  15. 2022Black-Box Tuning for Language-Model-as-a-Servicecited by 256
  16. 2021Get Your Vitamin C! Robust Fact Verification with Contrastive Evidencecited by 225
  17. 2020HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verificationcited by 201
  18. 2022On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoningcited by 194
  19. 2019MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claimscited by 169
  20. 2022The Unreliability of Explanations in Few-shot Prompting for Textual Reasoningcited by 169
  21. 2023Fact-Checking Complex Claims with Program-Guided Reasoningcited by 146
  22. 2023Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Frameworkcited by 139
  23. 2023Complex Claim Verification with Evidence Retrieved in the Wildcited by 110
  24. 2018DeClarE: Debunking Fake News and False Claims using Evidence-Aware Deep Learningcited by 100
  25. 2023Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Methodcited by 97
  26. 2024GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decodingcited by 75
  27. 2019A Richly Annotated Corpus for Different Tasks in Automated Fact-Checkingcited by 74
  28. 2021Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translationcited by 57
  29. 2020Generating Fact Checking Briefscited by 50
  30. 2022Tevatron: An Efficient and Flexible Toolkit for Dense Retrievalcited by 47
  31. 2022Missing Counter-Evidence Renders NLP Fact-Checking Unrealistic for Misinformationcited by 45
  32. 2021Zero-shot Fact Verification by Claim Generationcited by 42
  33. 2022Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedbackcited by 36
  34. 2024JustiLM: Few-shot Justification Generation for Explainable Fact-Checking of Real-world Claimscited by 29
  35. 2022Varifocal Question Generation for Fact-checkingcited by 27
  36. 2021Explainable Fact-checking through Question Answeringcited by 16
  37. 2022ngram-OAXE: Phrase-Based Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translationcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 7; 2026: 4.

15 papers.

Sort:

By area:

  1. 2024Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMscited by 96
  2. 2024Claim Verification in the Age of Large Language Models: A Surveycited by 24
  3. 2024ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systemscited by 23
  4. 2025Resolving Conflicting Evidence in Automated Fact-Checking: A Study on Retrieval-Augmented LLMscited by 16
  5. 2025Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Modelscited by 13
  6. 2025Evaluating open-source Large Language Models for automated fact-checkingcited by 6
  7. 2025Reasoning-CV: Fine-tuning Powerful Reasoning LLMs for Knowledge-Assisted Claim Verificationcited by 6
  8. 2024Reinforcement Tuning for Detecting Stances and Debunking Rumors Jointly with Large Language Modelscited by 5
  9. 2025Assessing the Potential of Generative Agents in Crowdsourced Fact-Checkingcited by 3
  10. 2025Fact in Fragments: Deconstructing Complex Claims via LLM-based Atomic Fact Extraction and Verificationcited by 2
  11. 2025Combating Biomedical Misinformation through Multi-modal Claim Detection and Evidence-based Verificationcited by 1
  12. 2026Diagnosing LLM Arbitration Behavior over Pre-evidence Epistemic States in RAG-based Fact-Checkingcited by 1
3 more
  1. 2026A Graph-Enhanced Defense Framework for Explainable Fake News Detection with LLMcited by 0
  2. 2026MedMeta: A Benchmark for LLMs in Synthesizing Meta-Analysis Conclusion from Medical Studiescited by 0
  3. 2026Principled Top-k Selection for Language Models with Hybrid Gradientscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Retrieval Augmented Fact Verification by Synthesizing Contrastive Arguments
  2. 2025Fact-checking AI-generated news reports: Can LLMs catch their own lies?
  3. 2026Context Shapes LLMs Retrieval-Augmented Fact-Checking Effectiveness
  4. 2024Provenance: A Light-weight Fact-checker for Retrieval Augmented LLM Generation Output
  5. 2026To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech
  6. 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents
  7. 2026Teaching Language Models to Check Grounded Claim Factuality with Human Test-Taking Strategies
  8. 2026Evaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence Ablation