most citedBED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design

1 citations · 1 across the 2 of their papers we have counts for

collaborators

5 papers

cs.LG2026

Loss-Driven Bayesian Active Learning

Zhuoyue Huang, Freddie Bickford Smith, Tom Rainforth

The central goal of active learning is to gather data that maximises downstream predictive performance, but popular approaches have limited flexibility in customising this data acq…

cs.CL20261 cited

BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design

Deepro Choudhury, Sinead Williamson, Adam Goliński +5

We propose a general-purpose approach for improving the ability of large language models (LLMs) to intelligently and adaptively gather information from a user or other external sou…

cs.LG2025

Prediction-Oriented Subsampling from Data Streams

Benedetta Lavinia Mussati, Freddie Bickford Smith, Tom Rainforth +1

Data is often generated in streams, with new observations arriving over time. A key challenge for learning models from data streams is capturing relevant information while keeping…

cs.LG2025

Scaling Up Active Testing to Large Language Models

Gabrielle Berrada, Jannik Kossen, Freddie Bickford Smith +3

Active testing enables label-efficient evaluation of predictive models through careful data acquisition, but it can pose a significant computational cost. We identify cost-saving m…

cs.LG2025

Rethinking Aleatoric and Epistemic Uncertainty

Freddie Bickford Smith, Jannik Kossen, Eleanor Trollope +3

The ideas of aleatoric and epistemic uncertainty are widely used to reason about the probabilistic predictions of machine-learning models. We identify incoherence in existing discu…