CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning
Reasoning Language Models (RLMs) have significantly improved performance on complex tasks by extending the reasoning chain. However, these chains are prone to containing factual errors, particularly in knowledge-intensive tasks. To address this issue, we propose CheckRLM, a framework that improves the reliability of the reasoning process through Retrieval-Augmented Generation (RAG) by timely checking and correcting factual errors. Specifically, CheckRLM extracts factual claims from the reasoning chain to identify and localize subtle knowledge inconsistencies during inference. Upon detection of
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorDingling Xu →
CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning
- Linked via arxiv authorRuobing Wang →
CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning
- Linked via arxiv authorQingfei Zhao →
CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning
- Linked via arxiv authorYukun Yan →
CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning
- Linked via arxiv authorZhichun Wang →
CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning
- Linked via arxiv authorDaren Zha →
CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning
- Linked via arxiv authorShi Yu →
CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning
- Linked via arxiv authorZhenghao Liu →
CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning
- Linked via arxiv authorShuo Wang →
CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning
- Linked via arxiv authorXu Han →
CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning
- Linked via arxiv authorMaosong Sun →
CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning