Neuron-level LLM Patching for Code Generation
- URL: http://arxiv.org/abs/2312.05356v3
- Date: Mon, 15 Apr 2024 07:31:00 GMT
- Title: Neuron-level LLM Patching for Code Generation
- Authors: Jian Gu, Aldeida Aleti, Chunyang Chen, Hongyu Zhang,
- Abstract summary: Large Language Models (LLMs) have found widespread adoption in software engineering, particularly in code generation tasks.
We propose a novel and effective model editing approach, textscMENT, to patch LLMs in coding tasks.
- Score: 32.178931149612644
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large Language Models (LLMs) have found widespread adoption in software engineering, particularly in code generation tasks. However, updating these models with new knowledge can be prohibitively expensive, yet it is essential for maximizing their utility. In this paper, we propose a novel and effective model editing approach, \textsc{MENT}, to patch LLMs in coding tasks. \textsc{MENT} is effective, efficient, and reliable. It can correct a neural model by patching 1 or 2 neurons. As the pioneer work on neuron-level model editing of generative models, we formalize the editing process and introduce the involved concepts. Besides, we also introduce new measures to evaluate its generalization ability, and build a benchmark for further study. Our approach is evaluated on three coding tasks, including API-seq recommendation, line-level code generation, and pseudocode-to-code transaction. The experimental results show that the proposed approach outperforms the state of the arts by a significant margin in both effectiveness and efficiency measures. In addition, we demonstrate the usages of \textsc{MENT} for LLM reasoning in software engineering. By editing LLM knowledge, the directly or indirectly dependent behaviors of API invocation in the chain-of-thought will change accordingly. It explained the significance of repairing LLMs.
Related papers
- One Token Can Help! Learning Scalable and Pluggable Virtual Tokens for Retrieval-Augmented Large Language Models [67.49462724595445]
Retrieval-augmented generation (RAG) is a promising way to improve large language models (LLMs)
We propose a novel method that involves learning scalable and pluggable virtual tokens for RAG.
arXiv Detail & Related papers (2024-05-30T03:44:54Z) - AI-powered Code Review with LLMs: Early Results [10.37036924997437]
We present a novel approach to improving software quality and efficiency through a Large Language Model (LLM)-based model.
Our proposed LLM-based AI agent model is trained on large code repositories.
It aims to detect code smells, identify potential bugs, provide suggestions for improvement, and optimize the code.
arXiv Detail & Related papers (2024-04-29T08:27:50Z) - Multi-Objective Fine-Tuning for Enhanced Program Repair with LLMs [16.890411067079885]
Large language models (LLMs) have demonstrated remarkable capabilities on a broad spectrum of downstream tasks.
We propose a novel perspective on the learning focus of LLM fine-tuning for program repair.
We apply MORepair to fine-tune four open-source LLMs with different sizes and architectures.
arXiv Detail & Related papers (2024-04-19T05:36:21Z) - Robust and Scalable Model Editing for Large Language Models [75.95623066605259]
We propose EREN (Edit models by REading Notes) to improve the scalability and robustness of LLM editing.
Unlike existing techniques, it can integrate knowledge from multiple edits, and correctly respond to syntactically similar but semantically unrelated inputs.
arXiv Detail & Related papers (2024-03-26T06:57:23Z) - Editing Conceptual Knowledge for Large Language Models [67.8410749469755]
This paper pioneers the investigation of editing conceptual knowledge for Large Language Models (LLMs)
We construct a novel benchmark dataset ConceptEdit and establish a suite of new metrics for evaluation.
experimental results reveal that, although existing editing methods can efficiently modify concept-level definition to some extent, they also have the potential to distort the related instantial knowledge.
arXiv Detail & Related papers (2024-03-10T16:57:10Z) - LLM Inference Unveiled: Survey and Roofline Model Insights [62.92811060490876]
Large Language Model (LLM) inference is rapidly evolving, presenting a unique blend of opportunities and challenges.
Our survey stands out from traditional literature reviews by not only summarizing the current state of research but also by introducing a framework based on roofline model.
This framework identifies the bottlenecks when deploying LLMs on hardware devices and provides a clear understanding of practical problems.
arXiv Detail & Related papers (2024-02-26T07:33:05Z) - Editing Large Language Models: Problems, Methods, and Opportunities [51.903537096207]
This paper embarks on a deep exploration of the problems, methods, and opportunities related to model editing for LLMs.
We provide an exhaustive overview of the task definition and challenges associated with model editing, along with an in-depth empirical analysis of the most progressive methods currently at our disposal.
Our objective is to provide valuable insights into the effectiveness and feasibility of each editing technique, thereby assisting the community in making informed decisions on the selection of the most appropriate method for a specific task or context.
arXiv Detail & Related papers (2023-05-22T16:00:00Z) - The Good, the Bad, and the Missing: Neural Code Generation for Machine
Learning Tasks [11.837851107416588]
This paper investigates the effectiveness of existing neural code generation models on Machine Learning programming tasks.
We select six state-of-the-art neural code generation models, and evaluate their performance on four widely used ML libraries.
Our empirical study reveals some good, bad, and missing aspects of neural code generation models on ML tasks.
arXiv Detail & Related papers (2023-05-16T00:52:02Z) - CodeRL: Mastering Code Generation through Pretrained Models and Deep
Reinforcement Learning [92.36705236706678]
"CodeRL" is a new framework for program synthesis tasks through pretrained LMs and deep reinforcement learning.
During inference, we introduce a new generation procedure with a critical sampling strategy.
For the model backbones, we extended the encoder-decoder architecture of CodeT5 with enhanced learning objectives.
arXiv Detail & Related papers (2022-07-05T02:42:15Z)
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.