7 papers
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…
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…
Observation-Free Attacks on Online Learning to Rank
Sameep Chattopadhyay, Nikhil Karamchandani, Sharayu Moharir
Online learning to rank (OLTR) plays a critical role in information retrieval and machine learning systems, with a wide range of applications in search engines and content recommen…
Low-Regret and Low-Complexity Learning for Hierarchical Inference
Sameep Chattopadhyay, Vinay Sutar, Jaya Prakash Champati +1
This work focuses on Hierarchical Inference (HI) in edge intelligence systems, where a compact Local-ML model on an end-device works in conjunction with a high-accuracy Remote-ML m…
AMPS: ASR with Multimodal Paraphrase Supervision
Abhishek Gupta, Amruta Parulekar, Sameep Chattopadhyay +1
Spontaneous or conversational multilingual speech presents many challenges for state-of-the-art automatic speech recognition (ASR) systems. In this work, we present a new technique…
Parameter-efficient Adaptation of Multilingual Multimodal Models for Low-resource ASR
Abhishek Gupta, Amruta Parulekar, Sameep Chattopadhyay +1
Automatic speech recognition (ASR) for low-resource languages remains a challenge due to the scarcity of labeled training data. Parameter-efficient fine-tuning and text-only adapta…
Algorithmic construction of Lyapunov functions for continuous vector fields via convex semi-infinite programs
Raavi Gupta, Sameep Chattopadhyay, Pradyumna Paruchuri +1
This article presents a novel numerically tractable technique for synthesizing Lyapunov functions for equilibria of nonlinear vector fields. In broad strokes, corresponding to an i…