QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization

Challenge:	Existing approaches to program repair are based on correctness alone.
Approach:	They propose a framework that mitigates over-editing and improves repair accuracy by generating buggy programs and re-edits.
Outcome:	The proposed framework improves repair precision by 31.4% under fix1@1, a metric that considers repair correctness and extent, and significantly increases decoding throughput when combined with speculative editing.

Similar Papers

Overview

Challenge

Approach

Outcome

Self-Edit: Fault-Aware Code Editor for Code Generation (2023.acl-long)

Copied to clipboard

Kechi Zhang, Zhuo Li, Jia Li, Ge Li, Zhi Jin

Programming Languages in NLP

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.

RePair: Automated Program Repair with Process-based Feedback (2024.findings-acl)

Copied to clipboard

Yuze Zhao, Zhenya Huang, Yixiao Ma, Rui Li, Kai Zhang, Hao Jiang, Qi Liu, Linbo Zhu, Yu Su

Language Models

Challenge:	Commercial-scale language models (LMs) have taken APR to unprecedented levels, but they are limited by parameters and humans interact with them through explicit prompts.
Approach:	They propose a method that utilizes process supervision to improve program repair by allowing users to input feedback from compilers and test cases.
Outcome:	The proposed method outperforms large outcome-based generation methods and is inspired by strategies used in programming competitions.

Repairing Regex Vulnerabilities via Localization-Guided Instructions (2026.eacl-long)

Copied to clipboard

Sicheol Sung, Joonghyuk Hahn, Yo-Sub Han

Language Models

Challenge:	Current approaches to regular expression denial of service (ReDoS) are hampered by a trade-off.
Approach:	They propose a framework to harness LLM generalization while enforcing reliability by localizing the vulnerable subpattern and generating a semanticallyequivalent fix for this isolated segment.
Outcome:	The proposed framework improves repair rates by 15.4%p over the state-of-the-art.

Code Reffix: A Benchmark for Reflection-Guided Code Repair with Large Language Models (2026.findings-acl)

Copied to clipboard

Zaiyuan Di, Jianting Chen, Yunxiao Yang, Xiaoying Gao, Li Yang, Zhihao Wang, Yang Xiang

Language Models

Challenge:	Existing benchmarks focus on the repair generation capability of LLMs, lacking fine-grained evaluation of reflection.
Approach:	They propose a benchmark with oracle reflections and a dual-task protocol to decouple evaluation of reflection from repair.
Outcome:	The proposed benchmarks show that underperforming reflection capabilities remain a bottleneck for code repair.

Course-Correction: Safety Alignment Using Synthetic Preferences (2024.emnlp-industry)

Copied to clipboard

Rongwu Xu, Yishuo Cai, Zhenhong Zhou, Renjie Gu, Haiqin Weng, Liu Yan, Tianwei Zhang, Wei Xu, Han Qiu

Responsible & Trustworthy NLP

Challenge:	Recent studies show that large language models generate harmful content, but the potential for generating harmful content is an escalating concern.
Approach:	They propose to fine-tune LLMs with preference learning to emphasize the preference for timely course-correction by using an automated pipeline.
Outcome:	The proposed model improves course-correction skills without affecting general performance and resists jailbreak attacks.

LaCo: Layer-wise Compensation for Pruned Large Language Models (2026.acl-long)

Copied to clipboard

Yingen Liu, Fan Wu, null Panxuyan, Ruihui Li, Zhuo Tang, Kenli Li

Language Models

Challenge:	Existing methods for predicting performance degradations of Large Language Models (LLMs) neglect the structural distortions caused by sparsity.
Approach:	They propose a framework that reorients the recovery paradigm from global adaptation to hierarchical representation alignment by sequentially optimizing each layer to reconstruct the model's hidden states.
Outcome:	The proposed framework surpasses parameter-efficient baselines in perplexity reduction and zero-shot reasoning.

GAPO: Robust Advantage Estimation for Real-World Code LLMs (2026.findings-acl)

Copied to clipboard

Jianqing Zhang, Zhezheng Hao, Wei Xia, Hande Dong, Hong Wang, Chenxing Wei, Yuyan Zhou, Yubin Qi, Qiang Lin, Jian Cao

Robustness in NLP

Challenge:	Reinforcement learning (RL) is widely used for post-training large language models (LLMs) in code editing, but in real-world code editing scenarios, reward distributions are often skewed with unpredictable noise, leading to distorted advantage computation and increased rollout outliers.
Approach:	They propose a group-relative method that finds an interval with the highest SNR and uses the median of that interval as an adaptive Q to replace the group mean in advantage calculation.
Outcome:	The proposed method improves on nine instruction-tuned LLMs while remaining plug-and-play and efficient.

Bridging the Editing Gap in LLMs: FineEdit for Precise and Targeted Text Modifications (2025.findings-emnlp)

Copied to clipboard

Yiming Zeng, Wanhao Yu, Zexin Li, Tao Ren, Yu Ma, Jinghan Cao, Xiyan Chen, Tingting Yu

Challenge:	a recent study shows that large language models can perform precise text editing tasks.
Approach:	InstrEditBench is a benchmark dataset that compares 30,000 structured editing tasks . experimental evaluations show FineEdit outperforms state-of-the-art models .
Outcome:	The proposed model outperforms state-of-the-art models on single-turn edits and mistral-7B-OpenOrca on direct edits.

SynthFix: Adaptive Neuro-Symbolic Code Vulnerability Repair (2026.findings-acl)

Copied to clipboard

Yifan Zhang, Jieyu Li, Kexin Pei, Yu Huang, Kevin Leach

Semantic Text Processing

Challenge:	Large Language Models (LLMs) struggle with complex semantic and structural correctness required for automated code repair.
Approach:	They propose a hybrid neural-symbolic framework that unifies code synthesis with compiler-informed symbolic feedback to improve LLM-based vulnerability repair.
Outcome:	The proposed framework improves code repair accuracy and efficiency over strong SFT and RFT training strategies on the FixJS and CodeFlaws benchmarks.

LlmFixer: Fix the Helpfulness of Defensive Large Language Models (2025.findings-emnlp)

Copied to clipboard

Zelong Yu, Xiaoming Zhang, Litian Zhang, Yu Yuan, Chaozhuo Li

Responsible & Trustworthy NLP

Challenge:	Several defense strategies have been introduced to defend against jailbreak attacks, but these strategies weakened the usefulness of large language models.
Approach:	They propose a framework that acts on large language models equipped with any defense strategy to recover their usefulness.
Outcome:	The proposed framework can be used on large language models to recover their usefulness without updating the parameters of a defensive large language model.