2 citations · 2 across the 6 of their papers we have counts for
7 papers
I'll Keep an Ear Out: Teaching AudioLLMs Proactive Audio Assistance
Amit Kumar Singh Yadav, Ritvik Shrivastava, Xuan Zhang +4
Audio large language models (AudioLLMs) operate reactively, responding only when queried. We introduce proactive audio assistance, where an AudioLLM monitors an audio stream and au…
Two-Level Meta-Rubrics for Evaluating Open-Ended Generation: GAMUT, a Benchmark for Factual Completeness
Xilun Chen, Zhaleh Feizollahi, Ross Goodwin +5
Rubric-based evaluation of open-ended generation faces a fundamental tension between expressiveness and reliability. Authoring a faithful rubric requires expressing the structure o…
Plan, Watch, Recover: A Benchmark and Architectures for Proactive Procedural Assistance
Kaustav Kundu, Ritvik Shrivastava, Maxim Arap +14
Proactive multimodal assistants must decide when guidance is needed and what to say, while tracking progress through extended procedures and helping users recover when they depart…
Doppelgänger's Watch: A Split Objective Approach to Large Language Models
Shervin Ghasemlou, Ashish Katiyar, Aparajita Saraf +5
In this paper, we investigate the problem of "generation supervision" in large language models, and present a novel bicameral architecture to separate supervision signals from thei…
Best Practices for Data-Efficient Modeling in NLG:How to Train Production-Ready Neural Models with Less Data
Ankit Arun, Soumya Batra, Vikas Bhardwaj +9
Natural language generation (NLG) is a critical component in conversational systems, owing to its role of formulating a correct and natural text response. Traditionally, NLG compon…
NoiseRank: Unsupervised Label Noise Reduction with Dependence Models
Karishma Sharma, Pinar Donmez, Enming Luo +2
Label noise is increasingly prevalent in datasets acquired from noisy channels. Existing approaches that detect and remove label noise generally rely on some form of supervision, w…
Unsupervised Supervised Learning II: Training Margin Based Classifiers without Labels
Krishnakumar Balasubramanian, Pinar Donmez, Guy Lebanon
Many popular linear classifiers, such as logistic regression, boosting, or SVM, are trained by optimizing a margin-based risk function. Traditionally, these risk functions are comp…