Publications

Publications by categories in reversed chronological order.

2026

  1. Improving Semantic Uncertainty Quantification in Language Model Question-Answering via Token-Level Temperature Scaling
    Tom A Lamb, Desi R Ivanova, Philip H S Torr, and Tim G J Rudner
    In The 29th International Conference on Artificial Intelligence and Statistics, 2026

2025

  1. Detecting LLM Hallucination Through Layer-wise Information Deficiency: Analysis of Ambiguous Prompts and Unanswerable Questions
    Hazel Kim, Tom A Lamb, Adel Bibi, Philip Torr, and Yarin Gal
    In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
  2. Can Large Language Models Express Uncertainty Like Human?
    Linwei Tao, Yi-Fan Yeh, Bo Kai, Minjing Dong, Tao Huang, and 4 more authors
    arXiv preprint arXiv:2509.24202, 2025
  3. Towards Label-Free Biological Reasoning Synthetic Dataset Creation via Uncertainty Filtering
    Josefa Lia Stoisser, Lawrence Phillips, Aditya Misra, Tom A LambPhilip Torr, and 3 more authors
    In NeurIPS Workshop on Efficient Reasoning, 2025
  4. Focus On This, Not That! Steering LLMs with Adaptive Feature Specification
    Tom A Lamb, Adam Davies, Alasdair Paren, Philip Torr, and Francesco Pinto
    In Forty-second International Conference on Machine Learning, 2025
  5. Semantic-Level Confidence Calibration of Language Models via Temperature Scaling
    Tom A Lamb, Desi R Ivanova, Philip Torr, and Tim GJ Rudner
    In ICLR Workshop: Quantify Uncertainty and Hallucination in Foundation Models: The Next Frontier in Reliable AI, 2025

2024

  1. Universal In-Context Approximation by Prompting Fully Recurrent Models
    Aleksandar Petrov, Tom Lamb, Alasdair Paren, Philip Torr, and Adel Bibi
    Advances in Neural Information Processing Systems, 2024
  2. Hidden in Plain Sight: Evaluating Abstract Shape Recognition in Vision-Language Models
    Arshia Hemmat, Adam Davies, Tom A Lamb, Jianhao Yuan, Philip Torr, and 2 more authors
    In The Thirty-eighth Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 2024

2023

  1. Faithful Knowledge Distillation
    Tom A Lamb, Rudy Brunel, Krishnamurthy DJ Dvijotham, M Pawan Kumar, Philip H S Torr, and 1 more author
    arXiv preprint arXiv:2306.04431, 2023