35 citations · 35 across the 8 of their papers we have counts for
9 papers
Interpreting Reasoning of Large Language Models via Partial Information Decomposition
Barproda Halder, Qiuyi Zhang, Sanghamitra Dutta
Large reasoning models (LRMs) have achieved substantial improvements in solving complex mathematical problems, but often produce lengthy, repetitive, or erroneous reasoning traject…
Reinforcement Learning under State and Outcome Uncertainty: A Foundational Distributional Perspective
Larry Preuett, Qiuyi Zhang, Muhammad Aurangzeb Ahmad
In many real-world planning tasks, agents must tackle uncertainty about the environment's state and variability in the outcomes of any chosen policy. We address both forms of uncer…
Prompts Generalize with Low Data: Non-vacuous Generalization Bounds for Optimizing Prompts with More Informative Priors
David Madras, Joshua Safyan, Qiuyi +1
Many prompt engineering techniques have been successful in practice, even when optimizing over a large prompt space with with a small amount of task-specific data. Recent work has…
Provable Distributional Value Iteration under Partial Observability
Larry Preuett, Qiuyi Zhang, Muhammad Aurangzeb Ahmad
In many real-world planning tasks, agents must tackle uncertainty about the environment's state and variability in the outcomes induced by stochastic dynamics and rewards. Motivate…
Optimized Tradeoffs for Private Prediction with Majority Ensembling
Shuli Jiang, Qiuyi, Zhang +1
We study a classical problem in private prediction, the problem of computing an -differentially private majority of -differentially private algorithms for $1 \…
Quantifying Knowledge Distillation Using Partial Information Decomposition
Pasan Dissanayake, Faisal Hamman, Barproda Halder +3
Knowledge distillation deploys complex machine learning models in resource-constrained environments by training a smaller student model to emulate internal representations of a com…
Ontology of Belief Diversity: A Community-Based Epistemological Approach
Tyler Fischella, Erin van Liemt, Qiuyi +1
AI applications across classification, fairness, and human interaction often implicitly require ontologies of social concepts. Constructing these well, especially when there are ma…
Towards Formalizing Spuriousness of Biased Datasets Using Partial Information Decomposition
Barproda Halder, Faisal Hamman, Pasan Dissanayake +3
Spuriousness arises when there is an association between two or more variables in a dataset that are not causally related. In this work, we propose an explainability framework to p…
Getting aligned on representational alignment
Ilia Sucholutsky, Lukas Muttenthaler, Adrian Weller +30
Biological and artificial information processing systems form representations of the world that they can use to categorize, reason, plan, navigate, and make decisions. How can we m…