6 papers
Logits are All We Need to Adapt Closed Models
Gaurush Hiranandani, Haolun Wu, Subhojyoti Mukherjee +1
Many commercial Large Language Models (LLMs) are often closed-source, limiting developers to prompt tuning for aligning content generation with specific applications. While these m…
FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain
Rohan Deb, Kiran Thekumparampil, Kousha Kalantari +3
Supervised fine-tuning (SFT) is a standard approach to adapting large language models (LLMs) to new domains. In this work, we improve the statistical efficiency of SFT by selecting…
An Efficient Plugin Method for Metric Optimization of Black-Box Models
Siddartha Devic, Nurendra Choudhary, Anirudh Srinivasan +3
Many machine learning algorithms and classifiers are available only via API queries as a ``black-box'' -- that is, the downstream user has no ability to change, re-train, or fine-t…
Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe
Kiran Koshy Thekumparampil, Gaurush Hiranandani, Kousha Kalantari +2
We study learning of human preferences from a limited comparison feedback. This task is ubiquitous in machine learning. Its applications such as reinforcement learning from human f…
All Against Some: Efficient Integration of Large Language Models for Message Passing in Graph Neural Networks
Ajay Jaiswal, Nurendra Choudhary, Ravinarayana Adkathimar +6
Graph Neural Networks (GNNs) have attracted immense attention in the past decade due to their numerous real-world applications built around graph-structured data. On the other hand…
Context-Aware Clustering using Large Language Models
Sindhu Tipirneni, Ravinarayana Adkathimar, Nurendra Choudhary +5
Despite the remarkable success of Large Language Models (LLMs) in text understanding and generation, their potential for text clustering tasks remains underexplored. We observed th…