LeTI: Learning to Generate from Textual Interactions

arXiv:2305.10314v2 Announce Type: replace
Abstract: Fine-tuning pre-trained language models (LMs) is essential for enhancing their capabilities. Existing techniques commonly fine-tune on input-output pairs (e.g., instruction tuning) or with numerical rewards that gauge the output quality (e.g., RLHF). We explore LMs' potential to learn from textual interactions (LETI) that not only check their correctness with binary labels but also pinpoint and explain errors in their outputs through textual feedback. Our focus is the code generation task, where the model produces code …

abstract arxiv capabilities check cs.ai cs.cl cs.se explore fine-tuning generate input-output interactions language language models learn lms numerical quality rlhf textual type