Large language models increasingly act through code, modifying repositories, executing programs, and interacting with services in agent form. Their actions introduce risks that cannot be assessed from generated responses alone. Safety evaluation must verify actual consequences, distinguish harm avoidance from task inca...
Wei-Tao Feng, Heng-Heng Xiong, Zi-Hao Zeng et al.· 0 citations
Conditional co-ablation (CoAx) is introduced, which ranks candidates by growth in ablation effect after primary-set removal, and coAx completions outperform matched random completions on all 8 non-GPT-2 models spanning 6 architecture families.
Z. Gong, He Lu, Tian-Tong Wang et al.· arXiv.org· 7 citations
State of Thought is proposed, a new reasoning paradigm that enables endogenous reasoning in LLMs, with the model's internal reasoning state governing how reasoning unfolds, and provides a generalizable and efficient alternative to existing test-time reasoning paradigms.
Z. Gong, Yi-Kun Hou, Zi-Hao Zeng et al.· 0 citations
CoCurve (Cross-Module Co-Pruning Curvature), a calibration-only, fine-tuning-free method that prunes attention and FFN units jointly, and reduces to one budgeted quadratic program, solved in a single shot under a shared attention--FFN budget, with no labels, fine-tuning, or recovery.
Z. Gong, Zihao Zeng, Zijie Wang et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
