Reasoning-CV

Code and datasets for a paper: Reasoning-CV: Fine-tuning Powerful Reasoning LLMs for Knowledge-Assisted Claim Verification

Introduction:

This repository includes training data, testing data, training scripts, testing scripts, and testing resultss. First, unzip the zip files to obtain complete data.

Training Data:

Refer to \trainingset for training data.

Testing Data:

Refer to \testset for testing data.

Training Scripts:

Refer to sft-lora.sh, sft-lora-dpo-stage3-guide.sh, sft-lora-dpo-stage3-guide2.sh for training scripts.

Testing Scripts:

For evaluation, run vllm-evaluate.py first for vericities with different LLMs, then run Judge_f1.py for F1 scores.

Testing Results:

\testset includes report results on some datasets. We will publish our LLMs on Huggingface afterward, and you can now run Judge_f1.py to get the F1 scores for these results.

Fine-tuned LLMs

See https://huggingface.co/zz1358m/Reasoning-CV to download LLMs for CoT-Verify and Decompose.