Weixun Wang, Bo Zheng, Jiaheng Liu, Xiaoshuai Song, Wenbo Su, Yanan Wu
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Self-Correction aims to enable large language models (LLMs) to self-verify and self-refine their initial responses without external feedback. However, LLMs often fail to effectively self-verify and generate correct feedback, further misleading refinement and leading to the failure of self-correction, especially in complex reasoning tasks. In this paper, we propose Program-driven Self-Correction (ProgCo). First, program-driven verification (ProgVe) achieves complex verification logic and extensive validation through self-generated, self-executing verification pseudo-programs. Then, program-driven refinement (ProgRe) receives feedback from ProgVe, conducts dual reflection and refinement on both responses and verification programs to mitigate misleading of incorrect feedback in complex reasoning tasks. Experiments on three instructionfollowing and mathematical benchmarks indicate that ProgCo achieves effective selfcorrection, and can be further enhance performance when combined with real program tools. We release our code at https://github.com/ songxiaoshuai/progco.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2501.01264")
get_code_for_paper("2501.01264")
have("2501.01264")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2501.01264.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2501.01264)
Connect an agent — have() is free.