Reasoning traces generated by large language models (LLMs) provide interpretability by exposing the factors that purportedly support their predictions. Such interpretability is important because model decisions may rely on spurious factors, and it can help practitioners identify such reliance and respond appropriately....
Jia-Lai Wang, Jun-Chen Lu, Song-Tao Yang et al.· Proceedings of the 41st IEEE...· 0 citations
PCodeTrans is presented, a dynamic feedback driven framework that implements a loop of recompilation, validation, and alignment for the recovery of functional source code that paves a practical path toward recovered source that can be recompiled, validated to pass test harnesses, and consumed by source-level security a...
Yu-Xin Cui, Ze-Yu Gao, Si-Liang Qin et al.· Proceedings of the 41st IEEE...· 0 citations
Software composition analysis (SCA) aims to identify third-party dependencies in programs, which plays a critical role in ensuring software supply chain security. Existing approaches largely follow a rule-based paradigm: they first compute function-level similarities, then aggregate these results using handcrafted heur...
Pei-Hong Li, Cheng Li, Yu-Chen Gu et al.· Proceedings of the ACM on So...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
