5 papers
CodeScout: Contextual Problem Statement Enhancement for Software Agents
Manan Suri, Xiangci Li, Mehdi Shojaie +5
Current AI-powered code assistance tools often struggle with poorly-defined problem statements that lack sufficient task context and requirements specification. Recent analysis of…
Online Posterior Sampling with a Diffusion Prior
Branislav Kveton, Boris Oreshkin, Youngsuk Park +2
Posterior sampling in contextual bandits with a Gaussian prior can be implemented exactly or approximately using the Laplace approximation. The Gaussian prior is computationally ef…
Optimal Design for Human Preference Elicitation
Subhojyoti Mukherjee, Anusha Lalitha, Kousha Kalantari +4
Learning of preference models from human feedback has been central to recent advances in artificial intelligence. Motivated by the cost of obtaining high-quality human annotations,…
Multi-Objective Alignment of Large Language Models Through Hypervolume Maximization
Subhojyoti Mukherjee, Anusha Lalitha, Sailik Sengupta +2
Multi-objective alignment from human feedback (MOAHF) in large language models (LLMs) is a challenging problem as human preferences are complex, multifaceted, and often conflicting…
Experimental Design for Active Transductive Inference in Large Language Models
Subhojyoti Mukherjee, Anusha Lalitha, Aniket Deshmukh +3
One emergent ability of large language models (LLMs) is that query-specific examples can be included in the prompt at inference time. In this work, we use active learning for adapt…