FSE 2025
Mon 23 - Fri 27 June 2025 Trondheim, Norway
co-located with ISSTA 2025
Mon 23 Jun 2025 17:00 - 17:20 at Andromeda - Repairs Chair(s): Michael Pradel

Not a day goes by without hearing about the impressive feats of large language models (LLMs), and equally, not a day passes without hearing about their challenges. LLMs are notoriously vulnerable to biases in their dataset, leading to issues such as toxicity, harmful responses, and factual inaccuracies. While domain-adaptive training has been employed to mitigate these issues, these techniques often address all model parameters indiscriminately during the repair process, resulting in poor repair quality and reduced model versatility. In this paper, drawing inspiration from fault localization via program slicing, we introduce a novel dynamic slicing-based intent-aware LLM repair strategy, IRepair. This approach selectively targets the most error-prone sections of the model for repair. Specifically, we propose dynamically slicing the model’s most sensitive layers that require immediate attention, concentrating repair efforts on those areas. This method enables more effective repairs with potentially less impact on the model’s overall versatility by altering a smaller portion of the model. Furthermore, dynamic selection allows for a more nuanced and precise model repair compared to a fixed selection strategy. We evaluated our technique on three models from the GPT2 and GPT-Neo families, with parameters ranging from 800M to 1.6B, in a toxicity mitigation setup. Our results show that IRepair repairs errors 43.6% more effectively while causing 46% less disruption to general performance compared to the closest baseline, direct preference optimization. Our empirical analysis also reveals that errors are more concentrated in a smaller section of the model, with the top 20% of layers exhibiting 773% more error density than the remaining 80%. This highlights the need for selective repair. Additionally, we demonstrate that a dynamic selection approach is essential for addressing errors dispersed throughout the model, ensuring a robust and efficient repair.

Mon 23 Jun

Displayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change

16:00 - 18:00
RepairsResearch Papers / Journal First at Andromeda
Chair(s): Michael Pradel University of Stuttgart
16:00
20m
Talk
HornBro: Homotopy-like Method for Automated Quantum Program Repair
Research Papers
Siwei Tan Zhejiang University, Liqiang Lu Zhejiang University, Debin Xiang Zhejiang University, Tianyao Chu Zhejiang University, Congliang Lang Zhejiang University, Jintao Chen Zhejiang University, Xing Hu Zhejiang University, Jianwei Yin Zhejiang University
DOI
16:20
20m
Talk
RePurr: Automated Repair of Block-Based Learners' Programs
Research Papers
Sebastian Schweikl University of Passau, Gordon Fraser University of Passau
DOI
16:40
20m
Talk
Demystifying Memorization in LLM-based Program Repair via a General Hypothesis Testing Framework
Research Papers
Jiaolong Kong Singapore Management University, Xiaofei Xie Singapore Management University, Shangqing Liu Nanyang Technological University
DOI
17:00
20m
Talk
IRepair: An Intent-Aware Approach to Repair Data-Driven Errors in Large Language Models
Research Papers
Sayem Mohammad Imtiaz Iowa State University, Astha Singh Dept. of Computer Science, Iowa State University, Fraol Batole Tulane University, Hridesh Rajan Tulane University
DOI
17:20
20m
Talk
Repairs and Breaks Prediction for Deep Neural Networks
Journal First
Yuta Ishimoto Kyushu University, Masanari Kondo Kyushu University, Lei Ma The University of Tokyo & University of Alberta, Naoyasu Ubayashi Waseda University, Yasutaka Kamei Kyushu University
17:40
20m
Talk
Element-Based Automated DNN Repair with Fine-Tuned Masked Language Model
Research Papers
Xu Wang Beihang University; Zhongguancun Laboratory; Ministry of Education, Mingming Zhang Beihang University, Xiangxin Meng Beihang University, Jian Zhang Nanyang Technological University, Yang Liu Nanyang Technological University, Chunming Hu Beihang University
DOI

Information for Participants
Mon 23 Jun 2025 16:00 - 18:00 at Andromeda - Repairs Chair(s): Michael Pradel
Info for room Andromeda:

Andromeda is located close to the restaurant and the bar, at the end of the corridor on the side of the bar.

From the registration desk, go towards the restaurant, turn left towards the bar, walk until the end of the corridor.

:
:
:
: