4 papers
Stop Training Against Soft Users: Mentalized Adversarial Self-Play for Proactive Dialogue
Zanwu Liu, Dan Zhang, Xiaodi Wang +6
Proactive dialogue agents must guide multi-turn interactions toward task goals while adapting to users whose intentions and attitudes evolve. Existing planners improve system side…
IB-RL: Isolated Bilateral Reinforcement Learning for Strategic Dialogue Agents
Senhao Wang, Chenghao Cai, Haitao Hu +4
Reinforcement learning (RL) has achieved strong results in improving large language models (LLMs) on tasks with stationary, verifiable rewards, such as mathematical reasoning and c…
The LLM Already Knows: Estimating LLM-Perceived Question Difficulty via Hidden Representations
Yubo Zhu, Dongrui Liu, Zecheng Lin +3
Estimating the difficulty of input questions as perceived by large language models (LLMs) is essential for accurate performance evaluation and adaptive inference. Existing methods…
Selective KV-Cache Sharing to Mitigate Timing Side-Channels in LLM Inference
Kexin Chu, Zecheng Lin, Dawei Xiang +7
Global KV-cache sharing is an effective optimization for accelerating large language model (LLM) inference, yet it introduces an API-visible timing side channel that lets adversari…