← back to paper

Review history

arxiv: 2507.22940 · 2 revisions

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes

1. 2026-08-15 REJECT MODERATE v1.4.0-alltime-deepseek-medium novelty 5.0
   87576 ms 38303 in 10437 out 2026-08-15T17:59:01.121711+00:00
2. 2026-08-06 REJECT MODERATE v1.4.0-alltime-deepseek-medium novelty 5.0
   144340 ms 38302 in 14270 out 2026-08-06T14:27:44.832197+00:00