Uncovering Weaknesses in Neural Code Generation

• URL: http://arxiv.org/abs/2407.09793v2
• Date: Wed, 17 Jul 2024 14:34:14 GMT
• Title: Uncovering Weaknesses in Neural Code Generation
• Authors: Xiaoli Lian, Shuaisong Wang, Jieping Ma, Fang Liu, Xin Tan, Li Zhang, Lin Shi, Cuiyun Gao,
• Abstract summary: We assess the quality of generated code using match-based and execution-based metrics, then conduct thematic analysis to develop a taxonomy of nine types of weaknesses. In the CoNaLa dataset, inaccurate prompts are a notable problem, causing all large models to fail in 26.84% of cases. Missing pivotal semantics is a pervasive issue across benchmarks, with one or more large models omitting key semantics in 65.78% of CoNaLa tasks. All models struggle with proper API usage, a challenge amplified by vague or complex prompts.
• Score: 21.552898575210534
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Code generation, the task of producing source code from prompts, has seen significant advancements with the advent of pre-trained large language models (PLMs). Despite these achievements, there lacks a comprehensive taxonomy of weaknesses about the benchmark and the generated code, which risks the community's focus on known issues at the cost of under-explored areas. Our systematic study aims to fill this gap by evaluating five state-of-the-art PLMs: three larger models, CodeGen2.5 with 7 billion parameters, CodeGeeX2 with 6 billion parameters, GPT-4 Turbo, and two smaller ones, UnixCoder with 110 million parameters and CodeT5 base with 220 million parameters, across three popular datasets, CoNaLa, HumanEval Plus, and DS-1000. We assess the quality of generated code using match-based and execution-based metrics, then conduct thematic analysis to develop a taxonomy of nine types of weaknesses. We dissected weakness distributions in both larger and smaller models, applying an extensive methodology that encompasses model-specific as well as collective analysis (union and intersection) across models. Our research uncovers three salient findings: 1. In the CoNaLa dataset, inaccurate prompts are a notable problem, causing all large models to fail in 26.84% of cases, with even higher failure rates of 40% for smaller models; 2. Missing pivotal semantics is a pervasive issue across benchmarks, with one or more large models omitting key semantics in 65.78% of CoNaLa tasks, and similarly high occurrences in HumanEval Plus (66.09%) and DS-1000 (80.51%); 3. All models struggle with proper API usage, a challenge amplified by vague or complex prompts. Our findings aim to steer researchers towards addressing specific weaknesses and challenges in code generation. Furthermore, our annotations can offer a targeted benchmark subset for detailed analysis.

Related papers

• CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models [91.15135237584771]
  Large language models (LLMs) can act as agents with capabilities to self-refine and improve generated code autonomously. We propose CodeTree, a framework for LLM agents to efficiently explore the search space in different stages of the code generation process. Specifically, we adopted a unified tree structure to explicitly explore different coding strategies, generate corresponding coding solutions, and subsequently refine the solutions.
  arXiv  Detail & Related papers  (2024-11-07T00:09:54Z)
• SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models [54.78329741186446]
  We propose a novel paradigm that uses a code-based critic model to guide steps including question-code data construction, quality control, and complementary evaluation. Experiments across both in-domain and out-of-domain benchmarks in English and Chinese demonstrate the effectiveness of the proposed paradigm.
  arXiv  Detail & Related papers  (2024-08-28T06:33:03Z)
• Exploring RAG-based Vulnerability Augmentation with LLMs [19.45598962972431]
  Large language models (LLMs) are being used for solving various code generation and comprehension tasks. In this study, we explore three different strategies to augment vulnerabilities, with LLMs, namely Mutation, Injection, and Extension. Our results show that our injection-based clustering-enhanced RAG method beats the baseline setting (NoAug), Vulgen, and VGX (two SOTA methods), and Random Oversampling (ROS) by 30.80%, 27.48%, 27.93%, and 15.41% in f1-score with 5K generated vulnerable samples.
  arXiv  Detail & Related papers  (2024-08-07T23:22:58Z)
• What's Wrong with Your Code Generated by Large Language Models? An Extensive Study [80.18342600996601]
  Large language models (LLMs) produce code that is shorter yet more complicated as compared to canonical solutions. We develop a taxonomy of bugs for incorrect codes that includes three categories and 12 sub-categories, and analyze the root cause for common bug types. We propose a novel training-free iterative method that introduces self-critique, enabling LLMs to critique and correct their generated code based on bug types and compiler feedback.
  arXiv  Detail & Related papers  (2024-07-08T17:27:17Z)
• DiscoveryBench: Towards Data-Driven Discovery with Large Language Models [50.36636396660163]
  We present DiscoveryBench, the first comprehensive benchmark that formalizes the multi-step process of data-driven discovery. Our benchmark contains 264 tasks collected across 6 diverse domains, such as sociology and engineering. Our benchmark, thus, illustrates the challenges in autonomous data-driven discovery and serves as a valuable resource for the community to make progress.
  arXiv  Detail & Related papers  (2024-07-01T18:58:22Z)
• MapCoder: Multi-Agent Code Generation for Competitive Problem Solving [3.3856216159724983]
  We introduce a new approach to code generation tasks leveraging multi-agent prompting. Our framework, MapCoder, consists of four LLM agents specifically designed to emulate the stages of program synthesis. Our method consistently delivers superior performance across various programming languages.
  arXiv  Detail & Related papers  (2024-05-18T22:10:15Z)
• Do Neutral Prompts Produce Insecure Code? FormAI-v2 Dataset: Labelling Vulnerabilities in Code Generated by Large Language Models [3.4887856546295333]
  This study provides a comparative analysis of state-of-the-art large language models (LLMs) We analyze how likely they generate vulnerabilities when writing simple C programs using a neutral zero-shot prompt.
  arXiv  Detail & Related papers  (2024-04-29T01:24:14Z)
• Advancing LLM Reasoning Generalists with Preference Trees [119.57169648859707]
  We introduce Eurus, a suite of large language models (LLMs) optimized for reasoning. Eurus models achieve state-of-the-art results among open-source models on a diverse set of benchmarks.
  arXiv  Detail & Related papers  (2024-04-02T16:25:30Z)
• Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning [110.80663974060624]
  Key-Point-Driven Data Synthesis (KPDDS) is a novel data synthesis framework that synthesizes question-answer pairs. KPDDS ensures the generation of novel questions with rigorous quality control and substantial scalability. We present KPMath, an extensive synthetic dataset tailored for mathematical reasoning, comprising over 800K question-answer pairs.
  arXiv  Detail & Related papers  (2024-03-04T18:58:30Z)
• Language Models for Code Completion: A Practical Evaluation [13.174471984950857]
  This study provides both quantitative and qualitative assessments of three public code language models when completing real-world code. We collected real auto-completion usage data for over a year from more than 1200 users, resulting in over 600K valid completions. We found that 66.3% of failures were due to the models' limitations, 24.4% occurred due to inappropriate model usage in a development context, and 9.3% were valid requests that developers overwrote.
  arXiv  Detail & Related papers  (2024-02-25T20:43:55Z)
• DeepCode AI Fix: Fixing Security Vulnerabilities with Large Language Models [3.1690235522182104]
  Large language models (LLMs) are increasingly used to solve various programming tasks. We show that the task is difficult as it requires the model to learn long-range code relationships. We propose a technique to address these challenges with a new approach for querying and fine-tuning LLMs.
  arXiv  Detail & Related papers  (2024-02-19T18:35:40Z)

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.