Automatically Enhanced Instruction-following Capabilities of Large Language Models via Execution Feedback
Abstract: One core capability of large language models (LLMs) is to follow natural language instructions. However, the issue of automatically constructing high-quality training data to enhance the complex instruction-following abilities of LLMs without manual annotation remains unresolved. In this paper, we introduce AutoIF, the first scalable and reliable method for automatically generating instruction-following training data. AutoIF transforms the validation of instruction-following data quality into code verification, requiring LLMs to generate instructions, the corresponding code to check the correctness of the instruction responses, and unit test samples to verify the code's correctness. Then, execution feedback-based rejection sampling can generate data for Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) training. AutoIF achieves significant improvements across three training algorithms, SFT, Offline DPO, and Online DPO, when applied to the top open-source LLMs, Qwen2 and Llama3, in self-alignment and strong-to-weak distillation settings.
Paper Type: Long
Research Area: Dialogue and Interactive Systems
Research Area Keywords: Instruction Following, Large Language Models, Execution Feedback, On-policy Learning, Strong-to-Weak Distillation, Self-Alignment
Contribution Types: Model analysis & interpretability, NLP engineering experiment, Reproduction study, Approaches to low-resource settings, Approaches low compute settings-efficiency, Publicly available software and/or pre-trained models, Data resources, Data analysis
Languages Studied: English
Submission Number: 4837
Loading