3 papers
cs.AI2026
AdaGuard: Enhancing Safety and Policy Compliance with Reasoning-Enabled LLM-As-A-Judge Guardrails
Melissa Kazemi Rad, Sihui Dai, Isha Slavin +6
Enterprise generative AI applications require robust safety mechanisms that can accommodate diverse risk postures, evolving policies, and varying latency constraints. Current guard…
cs.CL2026
Know When to Stop: Segment-Level Credit Assignment for Reducing Overthinking
Chia-Hsuan Lee, Sihui Dai, Mingyang Zhou +5
Reasoning language models frequently overthink: generating extended chains of behaviors such as hedging, approach abandonment, and self contradiction that consume tokens without im…
math.OC2022
Adapting Zeroth Order Algorithms for Comparison-Based Optimization
Isha Slavin, Daniel McKenzie
Comparison-Based Optimization (CBO) is an optimization paradigm that assumes only very limited access to the objective function f(x). Despite the growing relevance of CBO to real-w…