NExT: Teaching Large Language Models to Reason about Code Execution

• URL: http://arxiv.org/abs/2404.14662v1
• Date: Tue, 23 Apr 2024 01:46:32 GMT
• Title: NExT: Teaching Large Language Models to Reason about Code Execution
• Authors: Ansong Ni, Miltiadis Allamanis, Arman Cohan, Yinlin Deng, Kensen Shi, Charles Sutton, Pengcheng Yin,
• Abstract summary: Large language models (LLMs) of code are typically trained on the surface textual form of programs. We propose NExT, a method to teach LLMs to inspect the execution traces of programs and reason about their run-time behavior.
• Score: 50.93581376646064
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A fundamental skill among human developers is the ability to understand and reason about program execution. As an example, a programmer can mentally simulate code execution in natural language to debug and repair code (aka. rubber duck debugging). However, large language models (LLMs) of code are typically trained on the surface textual form of programs, thus may lack a semantic understanding of how programs execute at run-time. To address this issue, we propose NExT, a method to teach LLMs to inspect the execution traces of programs (variable states of executed lines) and reason about their run-time behavior through chain-of-thought (CoT) rationales. Specifically, NExT uses self-training to bootstrap a synthetic training set of execution-aware rationales that lead to correct task solutions (e.g., fixed programs) without laborious manual annotation. Experiments on program repair tasks based on MBPP and HumanEval demonstrate that NExT improves the fix rate of a PaLM 2 model, by 26.1% and 14.3% absolute, respectively, with significantly improved rationale quality as verified by automated metrics and human raters. Our model can also generalize to scenarios where program traces are absent at test-time.

Related papers

• Learning to Reason via Program Generation, Emulation, and Search [33.11955431589091]
  Program synthesis with language models (LMs) has unlocked a large set of reasoning abilities. Not all reasoning tasks are easily expressible as code, e.g. tasks involving commonsense reasoning, moral decision-making, and sarcasm understanding. We propose Code Generation and Emulated EXecution (CoGEX) to extend an LM's program synthesis skills to such tasks.
  arXiv  Detail & Related papers  (2024-05-25T19:40:50Z)
• A Static Evaluation of Code Completion by Large Language Models [65.18008807383816]
  Execution-based benchmarks have been proposed to evaluate functional correctness of model-generated code on simple programming problems. static analysis tools such as linters, which can detect errors without running the program, haven't been well explored for evaluating code generation models. We propose a static evaluation framework to quantify static errors in Python code completions, by leveraging Abstract Syntax Trees.
  arXiv  Detail & Related papers  (2023-06-05T19:23:34Z)
• Understanding Programs by Exploiting (Fuzzing) Test Cases [26.8259045248779]
  We propose to incorporate the relationship between inputs and possible outputs/behaviors into learning, for achieving a deeper semantic understanding of programs. To obtain inputs that are representative enough to trigger the execution of most part of the code, we resort to fuzz testing and propose fuzz tuning. The effectiveness of the proposed method is verified on two program understanding tasks including code clone detection and code classification, and it outperforms current state-of-the-arts by large margins.
  arXiv  Detail & Related papers  (2023-05-23T01:51:46Z)
• Fully Autonomous Programming with Large Language Models [0.9558392439655015]
  Current approaches to program synthesis with Large Language Models (LLMs) exhibit a "near miss syndrome" We use OpenAI Codex as the LLM and Program Synthesis Benchmark 2 as a database of problem descriptions and tests for evaluation. The resulting framework outperforms both conventional usage of Codex without the repair phase and traditional genetic programming approaches.
  arXiv  Detail & Related papers  (2023-04-20T16:12:05Z)
• Fault-Aware Neural Code Rankers [64.41888054066861]
  We propose fault-aware neural code rankers that can predict the correctness of a sampled program without executing it. Our fault-aware rankers can significantly increase the pass@1 accuracy of various code generation models.
  arXiv  Detail & Related papers  (2022-06-04T22:01:05Z)
• Learning from Self-Sampled Correct and Partially-Correct Programs [96.66452896657991]
  We propose to let the model perform sampling during training and learn from both self-sampled fully-correct programs and partially-correct programs. We show that our use of self-sampled correct and partially-correct programs can benefit learning and help guide the sampling process. Our proposed method improves the pass@k performance by 3.1% to 12.3% compared to learning from a single reference program with MLE.
  arXiv  Detail & Related papers  (2022-05-28T03:31:07Z)
• Natural Language to Code Translation with Execution [82.52142893010563]
  Execution result--minimum Bayes risk decoding for program selection. We show that it improves the few-shot performance of pretrained code models on natural-language-to-code tasks.
  arXiv  Detail & Related papers  (2022-04-25T06:06:08Z)
• Measuring Coding Challenge Competence With APPS [54.22600767666257]
  We introduce APPS, a benchmark for code generation. Our benchmark includes 10,000 problems, which range from having simple one-line solutions to being substantial algorithmic challenges. Recent models such as GPT-Neo can pass approximately 15% of the test cases of introductory problems.
  arXiv  Detail & Related papers  (2021-05-20T17:58:42Z)

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.