Grounding Code Generation with Input-Output Specifications
Primary Area: neurosymbolic & hybrid AI systems (physics-informed, logic & formal reasoning, etc.)
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: code generation, I/O specifications, instruction tuning
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: A new framework for instruction fine-tuning large language models of code in which the training is guided by execution based I/O specifications.
Abstract: Large language models (LLMs) have demonstrated significant potential in code generation. However, the code generated by these models occasionally deviates from the user's intended outcome, resulting in executable but incorrect code. To mitigate this issue, we propose GIFT4Code, a novel approach for the instruction fine-tuning of LLMs specifically tailored for code generation. Our method leverages synthetic data produced by the LLM itself and utilizes execution-derived feedback as a key learning signal. This feedback, in the form of program input-output specifications, is provided to the LLM to facilitate fine-tuning. We evaluated our approach on two challenging data science benchmarks, Arcade and DS-1000. Our results suggest that the method enhances the LLM's alignment with user intentions, considerably reducing the incidence of executable but incorrect outputs. Consequently, this leads to a marked improvement in the quality of generated code.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 6594
Loading