Showing 2026Show all
2 papers · 1 filter
cs.CL2026
Pushback in a Haystack: Language Models Respond to Factual Errors Ambiguously and Ineffectively
Li Lucy, Myra Cheng, Svenja Guhr +7
The sycophancy of language models, or their failure to push back against faulty user input, is now widely studied. However, if LMs do push back, is sycophancy solved? We show that…
cs.LG2026
Beyond Fresh Starts: Stateful Inference for Streaming ASR in Conversational Voice Agents
Sameep Chattopadhyay, Alexander Erdmann, Mari Ostendorf
Modern voice-agent systems rely on streaming speech recognition models that operate under stringent latency constraints. This study shows that, due to the limited memory constraint…