5 papers
Can Large Language Models Model Programs Formally?
Zhiyong Chen, Jialun Cao, Jiarong Wu +2
In the digital age, ensuring the correctness, safety, and reliability of software through formal verification is paramount, particularly as software increasingly underpins critical…
ModelWisdom: An Integrated Toolkit for TLA+ Model Visualization, Digest and Repair
Zhiyong Chen, Jialun Cao, Chang Xu +1
Model checking in TLA+ provides strong correctness guarantees, yet practitioners continue to face significant challenges in interpreting counterexamples, understanding large state-…
TriSpec: Ternary Speculative Decoding via Lightweight Proxy Verification
Haoyun Jiang, Junqi He, Feng Hong +8
Inference efficiency in Large Language Models (LLMs) is fundamentally limited by their serial, autoregressive generation, especially as reasoning becomes a key capability and respo…
AetherCode: Evaluating LLMs' Ability to Win In Premier Programming Competitions
Zihan Wang, Jiaze Chen, Zhicheng Liu +25
Competitive programming has emerged as a critical benchmark for evaluating the reasoning and coding capabilities of Large Language Models (LLMs). Despite impressive progress on exi…
JavaBench: A Benchmark of Object-Oriented Code Generation for Evaluating Large Language Models
Jialun Cao, Zhiyong Chen, Jiarong Wu +2
Code generation benchmarks such as HumanEval are widely adopted to evaluate LLMs' capabilities. However, after consolidating the latest 24 benchmarks, we noticed three significant…