LMPL 2025 – Proceedings

Reasoning as a Resource: Optimizing Fast and Slow Thinking in Code Generation Models
Zongjie Li and Shuai Wang
(Hong Kong University of Science and Technology, China)

Publisher's Version Article: splashws25lmplmain-p4-p (type: Full Paper (5 pages, references excluded)) doi:10.1145/3759425.3763377

Hallucination-Resilient LLM-Driven Sound and Tunable Static Analysis: A Case of Higher-Order Control-Flow Analysis
Guannan Wei, Zhuo Zhang, and Caterina Urban
(Inria, France; ENS-PSL University, France; Tufts University, USA; Columbia University, USA)

Publisher's Version Article: splashws25lmplmain-p7-p (type: Full Paper (5 pages, references excluded)) doi:10.1145/3759425.3763378

Hallucination-Resilient LLM-Driven Sound and Tunable Static Analysis: Recorded video presentation of "Hallucination-Resilient LLM-Driven Sound and Tunable Static Analysis". Presentation at the LMPL 2025 workshop, October 15, 2025, https://conf.researchr.org/home/icfp-splash-2025/lmpl-2025

CG-Bench: Can Language Models Assist Call Graph Construction in the Real World?
Ting Yuan, Wenrui Zhang, Dong Chen, and Jie Wang
(Huawei Technologies, China)

Publisher's Version Article: splashws25lmplmain-p9-p (type: Full Paper (5 pages, references excluded)) doi:10.1145/3759425.3763379

CG-Bench: Can Language Models Assist Call Graph Construction in the Real World?: Recorded video presentation of "CG-Bench: Can Language Models Assist Call Graph Construction in the Real World?". Presentation at the LMPL 2025 workshop, October 15, 2025, https://conf.researchr.org/home/icfp-splash-2025/lmpl-2025

Challenges in C++ to Rust Translation with Large Language Models: A Preliminary Empirical Study
Yanyan Yan, Yang Feng, Qi He, Jun Zeng, and Baowen Xu
(Nanjing University, China)

Publisher's Version Article: splashws25lmplmain-p10-p (type: Full Paper (5 pages, references excluded)) doi:10.1145/3759425.3763380

Challenges in C++ to Rust Translation with Large Language Models: A Preliminary Empirical Study: Recorded video presentation of "Challenges in C++ to Rust Translation with Large Language Models: A Preliminary Empirical Study". Presentation at the LMPL 2025 workshop, October 15, 2025, https://conf.researchr.org/home/icfp-splash-2025/lmpl-2025

Programming Language Techniques for Bridging LLM Code Generation Semantic Gaps
Yalong Du, Chaozheng Wang, and Huaijin Wang
(Harbin Institute of Technology, Shenzhen, China; Chinese University of Hong Kong, China; Hong Kong University of Science and Technology, China)

Publisher's Version Article: splashws25lmplmain-p13-p (type: Full Paper (5 pages, references excluded)) doi:10.1145/3759425.3763383

Ranking Formal Specifications using LLMs
Mike He, Zhendong Ang, Ankush Desai, and Aarti Gupta
(Princeton University, USA; National University of Singapore, Singapore; Amazon Web Services, USA)

Publisher's Version Article: splashws25lmplmain-p22-p (type: Full Paper (5 pages, references excluded)) doi:10.1145/3759425.3763386

Ranking Formal Specifications using LLMs: Recorded video presentation of "Ranking Formal Specifications using LLMs". Presentation at the LMPL 2025 workshop, October 15, 2025, https://conf.researchr.org/home/icfp-splash-2025/lmpl-2025

Improving SAST Detection Capability with LLMs and Enhanced DFA
Yuan Luo, Zhaojun Chen, Yuxin Dong, Haiquan Zhang, Yi Sun, Fei Xie, and Zhiqiang Dong
(Tencent Security Yunding Lab, China; Peking University, China)

Publisher's Version Article: splashws25lmplmain-p26-p (type: Full Paper (5 pages, references excluded)) doi:10.1145/3759425.3763388

A Case Study on the Effectiveness of LLMs in Verification with Proof Assistants
Barış Bayazıt, Yao Li, and Xujie Si
(University of Toronto, Canada; Portland State University, USA)

Publisher's Version

Published Artifact

Artifacts Available Article: splashws25lmplmain-p35-p (type: Full Paper) doi:10.1145/3759425.3763391

	A Case Study on the Effectiveness of LLMs in Verification with Proof Assistants: Recorded video presentation of "A Case Study on the Effectiveness of LLMs in Verification with Proof Assistants". Presentation at the LMPL 2025 workshop, October 15, 2025, https://conf.researchr.org/home/icfp-splash-2025/lmpl-2025
	Replication Package for "A Case Study on the Effectiveness of LLMs in Verification with Proof Assistants" (doi:10.5281/zenodo.16939067): Codebase used to obtain the results described in the paper.

The Modular Imperative: Rethinking LLMs for Maintainable Software
Anastasiya Kravchuk-Kirilyuk, Fernanda Graciolli, and Nada Amin
(Harvard University, USA; Midspiral, USA)

Publisher's Version Article: splashws25lmplmain-p52-p (type: Full Paper (5 pages, references excluded)) doi:10.1145/3759425.3763392

The Modular Imperative: Rethinking LLMs for Maintainable Software: Recorded video presentation of "The Modular Imperative: Rethinking LLMs for Maintainable Software". Presentation at the LMPL 2025 workshop, October 15, 2025, https://conf.researchr.org/home/icfp-splash-2025/lmpl-2025

Enhancing Semantic Understanding in Pointer Analysis using Large Language Models
Baijun Cheng, Kailong Wang, Ling Shi, Haoyu Wang, Yao Guo, Ding Li, and Xiangqun Chen
(Peking University, China; Huazhong University of Science and Technology, China; Nanyang Technological University, Singapore)

Publisher's Version Article: splashws25lmplmain-p53-p (type: Full Paper (5 pages, references excluded)) doi:10.1145/3759425.3763393

Preguss: It Analyzes, It Specifies, It Verifies
Zhongyi Wang, Tengjie Lin, Mingshuai Chen, Mingqi Yang, Haokun Li, Xiao Yi, Shengchao Qin, and Jianwei Yin
(Zhejiang University, China; Peking University, China; Chinese University of Hong Kong, China; Xidian University, China)

Publisher's Version Article: splashws25lmplmain-p55-p (type: Full Paper (5 pages, references excluded)) doi:10.1145/3759425.3763394

Preguss: It Analyzes, It Specifies, It Verifies: Recorded video presentation of "Preguss: It Analyzes, It Specifies, It Verifies". Presentation at the LMPL 2025 workshop, October 15, 2025, https://conf.researchr.org/home/icfp-splash-2025/lmpl-2025

Composable Effect Handling for Programming LLM-Integrated Scripts
Di Wang
(Peking University, China)

Publisher's Version Article: splashws25lmplmain-p65-p (type: Full Paper (5 pages, references excluded)) doi:10.1145/3759425.3763396

Composable Effect Handling for Programming LLM-integrated Scripts: Recorded video presentation of "Composable Effect Handling for Programming LLM-integrated Scripts". Presentation at the LMPL 2025 workshop, October 15, 2025, https://conf.researchr.org/home/icfp-splash-2025/lmpl-2025

ClearAgent: Agentic Binary Analysis for Effective Vulnerability Detection
Xiang Chen, Anshunkang Zhou, Chengfeng Ye, and Charles Zhang
(Hong Kong University of Science and Technology, China)

Publisher's Version Article: splashws25lmplmain-p90-p (type: Full Paper (5 pages, references excluded)) doi:10.1145/3759425.3763397

ClearAgent: Agentic Binary Analysis for Effective Vulnerability Detection: Recorded video presentation of "ClearAgent: Agentic Binary Analysis for Effective Vulnerability Detection". Presentation at the LMPL 2025 workshop, October 15, 2025, https://conf.researchr.org/home/icfp-splash-2025/lmpl-2025

W2GPU: Toward WebAssembly-to-WebGPU Program Translation via Small Language Models
Mehmet Oguz Derin
(Unaffiliated, Türkiye)

Publisher's Version

Info Article: splashws25lmplmain-p93-p (type: Full Paper (5 pages, references excluded)) doi:10.1145/3759425.3763398

W2GPU: Toward WebAssembly-to-WebGPU Program Translation via Small Language Models: Recorded video presentation of "W2GPU: Toward WebAssembly-to-WebGPU Program Translation via Small Language Models". Presentation at the LMPL 2025 workshop, October 15, 2025, https://conf.researchr.org/home/icfp-splash-2025/lmpl-2025

LMPL 2025 – Proceedings

1st ACM SIGPLAN International Workshop on Language Models and Programming Languages (LMPL 2025)

Frontmatter

Papers