| Challenge: | Existing Large language models (LLMs) have low pass rates and accuracy on competitive programming tasks. |
| Approach: | They propose a generate-and-edit approach that uses execution results of generated code from LLMs to improve code quality on competitive programming tasks. |
| Outcome: | The proposed method improves 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. |
Similar Papers
Revisit Self-Debugging with Self-Generated Tests for Code Generation (2025.acl-long)
Copied to clipboard
Xiancai Chen, Zhengwei Tao, Kechi Zhang, Changzhi Zhou, Xinyu Zhang, Wanli Gu, Yuanpeng He, Mengdi Zhang, Xunliang Cai, Haiyan Zhao, Zhi Jin
| Challenge: | Large language models (LLMs) have made significant advances in code generation, but they still face challenges when tackling complex programming tasks beyond their basic capabilities. |
| Approach: | They propose to integrate self-generated tests into the code generation process . they propose to use post-execution and in-exection self-debugging to mitigate test bias . |
| Outcome: | The proposed method improves the performance of large language models in code generation tasks by leveraging execution feedback from tests. |
Can Large Language Models Invent Algorithms to Improve Themselves? (2025.naacl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown remarkable performance improvements, but the methods for improving LLMs are still designed by humans. |
| Approach: | They propose a framework which enables LLMs to generate and learn model-improvement algorithms by the seed model. |
| Outcome: | The proposed framework outperforms human-designed methods in model-improving tasks and improves the seed model by 6% and outperformed human-design methods by 4.3% on GSM8k. |
Improving Cross-Domain Low-Resource Text Generation through LLM Post-Editing: A Programmer-Interpreter Approach (2024.findings-eacl)
Copied to clipboard
| Challenge: | Large pre-trained language models such as GPT-3.5 and GPT-4 have gained significant attention in natural language research due to limited computational resources or inaccessible parameters. |
| Approach: | They propose a neural programmer-interpreter approach that preserves the domain generalization ability of LLMs while editing their output. |
| Outcome: | The proposed framework significantly improves GPT-3.5’s performance in logical form-to-text conversion and low-resource machine translation, surpassing other state-of-the-art (SOTA) LLM post-editing methods in cross-domain settings. |
UICoder: Finetuning Large Language Models to Generate User Interface Code through Automated Feedback (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing approaches to improve UI code generation rely on expensive human feedback or distilling a proprietary model. |
| Approach: | They propose to use automated feedback to guide large language models to generate UI code . they use a large synthetic dataset to generate improved models and refine them . |
| Outcome: | The proposed model outperforms baseline models and larger proprietary models . the model outpersforms models with automated metrics and human preferences . |
The Program Testing Ability of Large Language Models for Code (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Recent development of large language models (LLMs) for code shows promise in achieving code intelligence. |
| Approach: | They explore the ability of large language models to generate automated test cases . they show +11.77% and +4.22% higher code pass rates on HumanEval+ . |
| Outcome: | The proposed models show higher pass rates on humanEval+ compared with the current state-of-the-art models. |
CodeArena: A Collective Evaluation Platform for LLM Code Generation (2025.acl-demo)
Copied to clipboard
Mingzhe Du, Anh Tuan Luu, Bin Ji, Xiaobao Wu, Yuhao Qing, Dong Huang, Terry Yue Zhuo, Qian Liu, See-Kiong Ng
| Challenge: | Large Language Models (LLMs) have reshaped code generation, but persistent challenges impede accurate assessment. |
| Approach: | They propose an online evaluation framework tailored for large language models to assess their coding capabilities. |
| Outcome: | a new evaluation framework for large language models (LLMs) provides unbiased, unbiased evaluations and open access to solutions and test cases. |
CodeJudge: Evaluating Code Generation with Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown promising performance in code generation, but how to reliably evaluate code generated by LLMs remains a challenging problem. |
| Approach: | They propose a framework that leverages Large Language Models to evaluate the semantic correctness of generated code without the need for test cases. |
| Outcome: | The proposed framework outperforms existing methods on four code generation datasets and five programming languages. |
Editing Large Language Models: Problems, Methods, and Opportunities (2023.emnlp-main)
Copied to clipboard
Yunzhi Yao, Peng Wang, Bozhong Tian, Siyuan Cheng, Zhoubo Li, Shumin Deng, Huajun Chen, Ningyu Zhang
| Challenge: | Recent advances in model editing for LLMs have created challenges and opportunities for the community. |
| Approach: | They propose to alter the behavior of LLMs efficiently within a specific domain without negatively impacting performance across other inputs. |
| Outcome: | The proposed method alters behavior of LLMs efficiently within a specific domain without negatively impacting performance across other inputs. |
Can docstring reformulation with an LLM improve code generation? (2024.eacl-srw)
Copied to clipboard
| Challenge: | Existing approaches focus on training, fine-tuning or prompting LLMs to generate better outputs given the same input. |
| Approach: | They propose to optimize part of the input, the docstring, via reformulation with an LLM to improve code generation. |
| Outcome: | The proposed methods improve code generation on the original HumanEval benchmark and multiple curated variants on the same input. |
Idea First, Code Later: Disentangling Problem Solving from Code Generation in Evaluating LLMs for Competitive Programming (2026.findings-acl)
Copied to clipboard
Sama Hadhoud, Alaa Elsetohy, Frederikus Hudi, Jan Christian Blaise Cruz, Steven Halim, Alham Fikri Aji
| Challenge: | Existing evaluations conflate algorithmic reasoning with code-level implementation. |
| Approach: | They propose to center editorials in both solution generation and evaluation . they propose to compare editorials to gold standards and validate an LLM-as-a-judge protocol . |
| Outcome: | The proposed approach improves solve rates on some LLMs with gold editorials . but the gap between gold and generated editorials shows bottlenecks in implementation . |