metadata
license: llama3.1
base_model:
- meta-llama/Llama-3.1-8B-Instruct
RACE-CoT-Extractor-Llama-8B
This is the CoT-Extractor used in the paper "Joint Evaluation of Answer and Reasoning Consistency for Hallucination Detection in Large Reasoning Models," which extracts the long reasoning process of a reasoning model into a CoT that only includes essential steps.
For details on the prompt format, please refer to our GitHub repository.