Software libraries frequently evolve, introducing breaking changes that disrupt client applications. Existing detection approaches primarily target static programming languages or focus on syntactic changes, leaving behavioral breaking changes in dynamic languages such as Python underexplored. This task is particularly...
Wei Cheng, Chen Shen, Huan Zhang et al.· Proceedings of the ACM on So...· 0 citations
Chain-of-thought (CoT) monitoring provides a promising approach for detecting undesirable model behavior. Looped language models (LoopLMs) repeatedly apply shared transformer layers, increasing effective computational depth and enabling additional latent computation without increasing model size. However, the effect of...
Han Wang, Ishwar B. Balappanawar, Huan Zhang· 0 citations
MonitorBench is proposed, a systematic benchmark for evaluating CoT monitorability in LLMs and provides a basis for further research on AI control, reasoning faithfulness, stress-test monitorability, and monitoring scaffords.
Han Wang, Yi-Fan Sun, Brian Ko et al.· arXiv.org· 7 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.