Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions

• URL: http://arxiv.org/abs/2312.12450v6
• Date: Mon, 23 Sep 2024 19:57:18 GMT
• Title: Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions
• Authors: Federico Cassano, Luisa Li, Akul Sethi, Noah Shinn, Abby Brennan-Jones, Jacob Ginesin, Edward Berman, George Chakhnashvili, Anton Lozhkov, Carolyn Jane Anderson, Arjun Guha,
• Abstract summary: We introduce a benchmark of code editing tasks and use it to evaluate several cutting edge LLMs. Our evaluation exposes a significant gap between the capabilities of state-of-the-art open and closed models. We introduce a new, carefully curated, permissively licensed training dataset of code editing tasks coupled with natural language instructions.
• Score: 6.367360745627828
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A significant amount of research is focused on developing and evaluating large language models for a variety of code synthesis tasks. These include synthesizing code from natural language, synthesizing tests from code, and synthesizing explanations of code. In contrast, the behavior of instructional code editing with LLMs is understudied. These are tasks in which the model is provided a block of code and an instruction to modify the code. The editing instruction may ask for a feature to be added or removed, describe a bug and ask for a fix, or ask for a different kind of solution. We introduce a carefully crafted benchmark of code editing tasks and use it to evaluate several cutting edge LLMs. Our evaluation exposes a significant gap between the capabilities of state-of-the-art open and closed models. For example, even GPT-3.5-Turbo is better than the best open model at code editing tasks. We also introduce a new, carefully curated, permissively licensed training dataset of code editing tasks coupled with natural language instructions. Using this training dataset, we show that we can fine-tune open Code LLMs to significantly improve their code editing capabilities, closing the gap between open and closed models. All code, data, and models are available at https://github.com/nuprl/CanItEdit.

Related papers

• Beyond Code Generation: Assessing Code LLM Maturity with Postconditions [9.521621889147362]
  We propose a code Large Language Model maturity model based on the postcondition generation problem. We augment the EvalPlus dataset to a postcondition testing benchmark, and evaluate several open-sourced models.
  arXiv  Detail & Related papers  (2024-07-19T08:34:30Z)
• CodeUpdateArena: Benchmarking Knowledge Editing on API Updates [77.81663273436375]
  We present CodeUpdateArena, a benchmark for knowledge editing in the code domain. An instance in our benchmark consists of a synthetic API function update paired with a program synthesis example. Our benchmark covers updates of various types to 54 functions from seven diverse Python packages.
  arXiv  Detail & Related papers  (2024-07-08T17:55:04Z)
• CodeEditorBench: Evaluating Code Editing Capability of Large Language Models [49.387195629660994]
  Large Language Models (LLMs) for code are rapidly evolving, with code editing emerging as a critical capability. We introduce CodeEditorBench, an evaluation framework designed to rigorously assess the performance of LLMs in code editing tasks. We curate diverse coding challenges and scenarios from five sources, covering various programming languages, complexity levels, and editing tasks.
  arXiv  Detail & Related papers  (2024-04-04T15:49:49Z)
• InstructCoder: Instruction Tuning Large Language Models for Code Editing [26.160498475809266]
  We explore the use of Large Language Models (LLMs) to edit code based on user instructions. InstructCoder is the first instruction-tuning dataset designed to adapt LLMs for general-purpose code editing. Our findings reveal that open-source LLMs fine-tuned on InstructCoder can significantly enhance the accuracy of code edits.
  arXiv  Detail & Related papers  (2023-10-31T10:15:35Z)
• Coeditor: Leveraging Contextual Changes for Multi-round Code Auto-editing [57.776971051512234]
  In this work, we explore a multi-round code auto-editing setting, aiming to predict edits to a code region based on recent changes within the same. Our model, Coeditor, is a fine-tuned language model specifically designed for code editing tasks. In a simplified single-round, single-edit task, Coeditor significantly outperforms GPT-3.5 and SOTA open-source code completion models.
  arXiv  Detail & Related papers  (2023-05-29T19:57:36Z)
• GrACE: Generation using Associated Code Edits [23.643567386291988]
  We endowing pre-trained large language models (LLMs) of code with the knowledge of prior, relevant edits. The generative capability of the LLMs helps address the diversity in code changes and conditioning code generation on prior edits. We evaluate two well-known LLMs, Codex and CodeT5, in zero-shot and fine-tuning settings respectively.
  arXiv  Detail & Related papers  (2023-05-23T14:55:44Z)
• CodeT5+: Open Code Large Language Models for Code Understanding and Generation [72.1638273937025]
  Large language models (LLMs) pretrained on vast source code have achieved prominent progress in code intelligence. CodeT5+ is a family of encoder-decoder LLMs for code in which component modules can be flexibly combined to suit a wide range of downstream code tasks. We extensively evaluate CodeT5+ on over 20 code-related benchmarks in different settings, including zero-shot, finetuning, and instruction-tuning.
  arXiv  Detail & Related papers  (2023-05-13T14:23:07Z)
• InCoder: A Generative Model for Code Infilling and Synthesis [88.46061996766348]
  We introduce InCoder, a unified generative model that can perform program synthesis (via left-to-right generation) and editing (via infilling) InCoder is trained to generate code files from a large corpus of permissively licensed code. Our model is the first generative model that is able to directly perform zero-shot code infilling.
  arXiv  Detail & Related papers  (2022-04-12T16:25:26Z)
• CodeRetriever: Unimodal and Bimodal Contrastive Learning [128.06072658302165]
  We propose the CodeRetriever model, which combines the unimodal and bimodal contrastive learning to train function-level code semantic representations. For unimodal contrastive learning, we design a semantic-guided method to build positive code pairs based on the documentation and function name. For bimodal contrastive learning, we leverage the documentation and in-line comments of code to build text-code pairs.
  arXiv  Detail & Related papers  (2022-01-26T10:54:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.