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
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 61%Retrieval is underrated →
- PossiblePossibly related (embedding) · 56%Retrace-1.5B →
- PossiblePossibly related (embedding) · 54%Northwind AI →
- PossiblePossibly related (embedding) · 53%New benchmark exposes reasoning gaps in top models →
- PossiblePossibly related (embedding) · 49%Zefan-Cai/R-KV →
- LinkedLinked via arxiv author · 85%Dingling Xu →
“CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning”
- LinkedLinked via arxiv author · 85%Ruobing Wang →
“CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning”
- LinkedLinked via arxiv author · 85%Qingfei Zhao →
“CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning”