Pith. sign in

REVIEW 11 cited by

Self-Edit: Fault-Aware Code Editor for Code Generation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.04087 v5 pith:YA6A4U57 submitted 2023-05-06 cs.SE cs.CL

Kechi Zhang , Zhuo Li , Jia Li , Ge Li , Zhi Jin This is my paper · ORCID
classification cs.SEcs.CL
keywords codellmsprogrammingcompetitivegeneratedaccuracyapproachcomment
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Large language models (LLMs) have demonstrated an impressive ability to generate codes on competitive programming tasks. However, with limited sample numbers, LLMs still suffer from poor accuracy. Inspired by the process of human programming, we propose a generate-and-edit approach named Self-Edit that utilizes execution results of the generated code from LLMs to improve the code quality on the competitive programming task. We execute the generated code on the example test case provided in the question and wrap execution results into a supplementary comment. Utilizing this comment as guidance, our fault-aware code editor is employed to correct errors in the generated code. We perform extensive evaluations across two competitive programming datasets with nine different LLMs. Compared to directly generating from LLMs, our approach can improve the average of pass@1 by 89\% on APPS-dev, 31\% on APPS-test, and 48\% on HumanEval over nine popular code generation LLMs with parameter sizes ranging from 110M to 175B. Compared to other post-processing methods, our method demonstrates superior accuracy and efficiency.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Enhancing Code Generation via Bidirectional Comment-Level Mutual Grounding

    cs.SE 2025-05 conditional novelty 7.0 of 10

    An interactive code generation pipeline that uses editable inline comments as a feedback channel improves pass@1 on HumanEval/MBPP and user task success in a small study.

  2. SemOpt: LLM-Driven Code Optimization via Rule-Based Analysis

    cs.SE 2025-10 conditional novelty 6.0 of 10

    SemOpt generates Semgrep static-analysis rules from LLM-summarized optimization commits and uses them to locate and apply optimization strategies, outperforming retrieval-based baselines on C/C++ code.

  3. ReCode: Improving LLM-based Code Repair with Fine-Grained Retrieval-Augmented Generation

    cs.SE 2025-09 conditional novelty 6.0 of 10

    ReCode improves LLM-based code repair by combining algorithm-type prediction with dual-encoder retrieval of authentic bug-fix pairs, and introduces RACodeBench for evaluation.

  4. Dr. Boot: Bootstrapping Program Synthesis Language Models to Perform Repairing

    cs.SE 2025-07 conditional novelty 6.0 of 10

    A bootstrapping algorithm that trains program synthesis models on their own successful outputs and on repaired failures modestly improves pass@k over regular fine-tuning on MBPP, with mixed results on APPS.

  5. Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation

    cs.CL 2024-12 conditional novelty 6.0 of 10

    A tree-based, inference-only framework combining execution metrics with LLM self-critique improves code generation correctness and efficiency across models and benchmarks.

  6. AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement

    cs.LG 2024-12 reject novelty 6.0 of 10

    AlphaVerus bootstraps a Llama-70B model to generate Rust code that passes the Verus verifier by iteratively translating Dafny programs and refining candidates with tree search.

  7. Aligning Requirement for Large Language Model's Code Generation

    cs.SE 2025-09 conditional novelty 5.0 of 10

    An LLM-based specification-alignment method that lifts the model's perceived requirements from generated code and applies ten alignment rules improves Pass@1 by about 30% over existing baselines.

  8. Large Language Models for Next-Generation Wireless Network Management: A Survey and Tutorial

    cs.NI 2025-09 conditional novelty 4.0 of 10

    A survey and tutorial that organizes LLM-enabled wireless network optimization into formulation, solution, and verification stages, with case studies drawn from the authors' own prior papers.

  9. Towards Advancing Code Generation with Large Language Models: A Research Roadmap

    cs.SE 2025-01 conditional novelty 4.0 of 10

    A roadmap paper that organizes LLM code generation into a six-layer architecture and a four-phase human-in-the-loop workflow, and lists open challenges and recommendations.

  10. CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generation

    cs.SE 2025-01 conditional novelty 4.0 of 10

    CodeCoR improves LLM code generation by having four agents generate, test, prune, and repair candidate solutions, reporting a 77.8% average Pass@1 on four Python benchmarks.

  11. CoopetitiveV: Leveraging LLM-powered Coopetitive Multi-Agent Prompting for High-quality Verilog Generation

    cs.LG 2024-12 reject novelty 4.0 of 10

    A coopetitive multi-agent LLM framework, with a researcher, a prosecutor critic, and two revisers, pushes Verilog code generation to near-perfect pass rates on standard benchmarks.

Pith tools