activity
20242026
most citedLILO: Bayesian Optimization with Natural Language Feedback

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

collaborators

9 papers

cs.LG2026

Discovery of Hidden Miscalibration Regimes

Katarzyna Kobalczyk, Mihaela van der Schaar

Calibration is commonly evaluated by comparing model confidence with its empirical correctness, implicitly treating reliability as a function of the confidence score alone. However…

cs.LG20261 cited

LILO: Bayesian Optimization with Natural Language Feedback

Katarzyna Kobalczyk, Zhiyuan Jerry Lin, Benjamin Letham +3

Many real-world optimization problems are guided by complex, subjective preferences that are difficult to express as explicit closed-form objectives. In response, we introduce Lang…

cs.LG2026

Eliciting Numerical Predictive Distributions of LLMs Without Autoregression

Julianna Piskorz, Katarzyna Kobalczyk, Mihaela van der Schaar

Large Language Models (LLMs) have recently been successfully applied to regression tasks -- such as time series forecasting and tabular prediction -- by leveraging their in-context…

cs.LG2025

Interpretable Reward Modeling with Active Concept Bottlenecks

Sonia Laguna, Katarzyna Kobalczyk, Julia E. Vogt +1

We introduce Concept Bottleneck Reward Models (CB-RM), a reward modeling framework that enables interpretable preference learning through selective concept annotation. Unlike stand…

cs.AI2025

Preference Learning for AI Alignment: a Causal Perspective

Katarzyna Kobalczyk, Mihaela van der Schaar

Reward modelling from preference data is a crucial step in aligning large language models (LLMs) with human values, requiring robust generalisation to novel prompt-response pairs.…

cs.CL2025

The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data

Thomas Pouplin, Katarzyna Kobalczyk, Hao Sun +1

Developing autonomous agents capable of performing complex, multi-step decision-making tasks specified in natural language remains a significant challenge, particularly in realisti…