Publications

An up to date list of publications can be found on my Google Scholar profile.

2024

Understanding Chain-of-Thought in LLMs through Information Theory
J.F. Ton*, M.F. Taufiq*, Y. Liu
Preprint

Achievable Fairness on Your Data With Utility Guarantees
M.F. Taufiq, J.F. Ton, Y. Liu
NeurIPS 2024
Slides

2023

Marginal Density Ratio for Off-Policy Evaluation in Contextual Bandits
M.F. Taufiq, A. Doucet, R. Cornish, J.F. Ton
NeurIPS 2023
Slides

Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
Y. Liu*, Y. Yao*, J.F. Ton, X. Zhang, R. Guo, H. Cheng, Y. Klochkov, M.F. Taufiq, H. Li
NeurIPS 2023 Workshop on Socially Responsible Language Modelling Research (SoLaR).

Manifold Restricted Interventional Shapley Values
M.F. Taufiq, P. Blöbaum, L. Minorics
AISTATS 2023
Slides Video

Causal Falsification of Digital Twins
R. Cornish*, M.F. Taufiq*, A. Doucet, C. Holmes
Preprint
Slides

2022

Conformal Off-Policy Prediction in Contextual Bandits
M.F. Taufiq*, J.F. Ton*, R. Cornish, Y. W. Teh, A. Doucet
NeurIPS 2022
ICML 2022 Workshop on Distribution-Free Uncertainty Quantification (Spotlight).
Slides Video