# Co-FactChecker: A Framework for Human-AI Collaborative Claim Verification Using Large Reasoning Models

arXiv: https://arxiv.org/abs/2604.13706 · HTML: https://mlsanity.com/paper/2604.13706/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 26 of its 42 references that are in the map.
- First posted on arXiv 15 Apr 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 26 of 26)

- [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)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models](https://mlsanity.com/paper/2405.01535/) (2024)
- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [A Survey on Automated Fact-Checking](https://mlsanity.com/paper/2108.11896/) (2021)
- [ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search](https://mlsanity.com/paper/2406.03816/) (2024)
- [Inference-Time Scaling for Generalist Reward Modeling](https://mlsanity.com/paper/2504.02495/) (2025)
- [Automated Fact-Checking for Assisting Human Fact-Checkers](https://mlsanity.com/paper/2103.07769/) (2021)
- [CollabLLM: From Passive Responders to Active Collaborators](https://mlsanity.com/paper/2502.00640/) (2025)
- [Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers](https://mlsanity.com/paper/2311.09000/) (2023)
- [Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration](https://mlsanity.com/paper/2412.15701/) (2024)
- [Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers](https://mlsanity.com/paper/2502.20379/) (2025)
- [When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs](https://mlsanity.com/paper/2505.11423/) (2025)
- [FIRE: Fact-checking with Iterative Retrieval and Verification](https://mlsanity.com/paper/2411.00784/) (2024)
- [JustiLM: Few-shot Justification Generation for Explainable Fact-Checking of Real-world Claims](https://mlsanity.com/paper/2401.08026/) (2024)
- [Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checking](https://mlsanity.com/paper/2502.09083/) (2025)
- [LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey](https://mlsanity.com/paper/2505.00753/) (2025)
- [The simulation of judgment in LLMs](https://mlsanity.com/paper/2502.04426/) (2025)
- [Human and technological infrastructures of fact-checking](https://mlsanity.com/paper/2205.10894/) (2022)
- [ReasonIF: Large Reasoning Models Fail to Follow Instructions During Reasoning](https://mlsanity.com/paper/2510.15211/) (2025)
- [Can LLMs Automate Fact-Checking Article Writing?](https://mlsanity.com/paper/2503.17684/) (2025)
- [Expert Preference-based Evaluation of Automated Related Work Generation](https://mlsanity.com/paper/2508.07955/) (2025)
- [ThinkPilot: Steering Reasoning Models via Automated Think-prefixes Optimization](https://mlsanity.com/paper/2510.12063/) (2025)

## Built on by (most cited first, 1 of 1)

- [The FIL Hypothesis: Inductive Biases Help with Kernel Engineering](https://mlsanity.com/paper/2606.30442/) (2026)

## Abstract (arXiv)

Professional fact-checkers rely on domain knowledge and deep contextual understanding to verify claims. Large language models (LLMs) and large reasoning models (LRMs) lack such grounding and primarily reason from available evidence alone, creating a mismatch between expert-led and fully automated claim verification. To mitigate this gap, we posit human-AI collaboration as a more promising path forward, where expert feedback, grounded in real-world knowledge and domain expertise, guides the model's reasoning. However, existing LRMs are hard to calibrate to natural language feedback, particularly in a multi-turn interaction setup. We propose Co-FactChecker, a framework for human-AI collaborative claim verification. We introduce a new interaction paradigm that treats the model's thinking trace as a shared scratchpad. Co-FactChecker translates expert feedback into trace-edits that introduce targeted modifications to the trace, sidestepping the shortcomings of dialogue-based interaction. We provide theoretical results showing that trace-editing offers advantages over multi-turn dialogue, and our automatic evaluations demonstrate that Co-FactChecker outperforms existing autonomous and human-AI collaboration approaches. Human evaluations further show that Co-FactChecker is preferred over multi-turn dialogue, producing higher quality reasoning and verdicts along with relatively easier to interpret and more useful thinking traces.