2 papers
cs.LG2026
Autoregressive Decoding as a Martingale: Characterizing the Stochastic Dynamics of LLM Generation
Xiahui Zhu, Zhenyi Qi, Wanwei Liu +4
Large language models (LLMs) have achieved remarkable success across a wide range of language tasks. At their core, autoregressive LLMs are conditional probability models that lear…
cs.SE2026
Shapley-Guided Neural Repair Approach via Derivative-Free Optimization
Xinyu Sun, Wanwei Liu, Haoang Chi +7
DNNs are susceptible to defects like backdoors, adversarial attacks, and unfairness, undermining their reliability. Existing approaches mainly involve retraining, optimization, con…