intermediate reasoning steps
- CXReasonBench: A Benchmark for Evaluating Structured Diagnostic Reasoning in Chest X-rays
- CoT Information: Improved Sample Complexity under Chain-of-Thought Supervision
- Mind the Gap: Bridging Thought Leap for Improved Chain-of-Thought Tuning
- SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning