2 papers
cs.LG2026
Safety Game: Inference-Time Alignment of Black-Box LLMs via Constrained Optimization
Tuan Nguyen, Long Tran-Thanh
Ensuring that large language models (LLMs) comply with safety requirements is a central challenge in AI deployment. Existing alignment approaches primarily operate during training,…
cs.LG2026
Can Transformers Learn to Verify During Backtracking Search?
Yin Jun Phua, Tony Ribeiro, Tuan Nguyen +1
Backtracking search underlies classical constraint solvers, planners, and theorem provers. Recent transformer-based reasoning systems explore search trees over their own intermedia…