5 papers
Value-Aware Stochastic KV Cache Eviction for Reasoning Models
Ting-Yun Chang, Harvey Yiyun Fu, Deqing Fu +3
Reasoning models improve accuracy through extended chains of thought, but their long outputs create a memory and compute bottleneck. KV cache eviction methods reduce this cost by e…
Believing without Seeing: Quality Scores for Contextualizing Vision-Language Model Explanations
Keyu He, Tejas Srinivasan, Brihi Joshi +3
When people query Vision-Language Models (VLMs) but cannot see the accompanying visual context (e.g. for blind and low-vision users), augmenting VLM predictions with natural langua…
Adjust for Trust: Mitigating Trust-Induced Inappropriate Reliance on AI Assistance
Tejas Srinivasan, Jesse Thomason
Trust biases how users rely on AI recommendations in AI-assisted decision-making tasks, with low and high levels of trust resulting in increased under- and over-reliance, respectiv…
From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centered
Siddartha Devic, Tejas Srinivasan, Jesse Thomason +2
Large Language Models (LLMs) are increasingly assisting users in the real world, yet their reliability remains a concern. Uncertainty quantification (UQ) has been heralded as a too…
Better Slow than Sorry: Introducing Positive Friction for Reliable Dialogue Systems
Mert Ä°nan, Anthony Sicilia, Suvodip Dey +6
While theories of discourse and cognitive science have long recognized the value of unhurried pacing, recent dialogue research tends to minimize friction in conversational systems.…