4 papers
Online Conformal Prediction Beyond Feedback
Joar Skalse, Edoardo Pona, Osvaldo Simeone +1
Online conformal prediction (OCP) provides theoretically principled uncertainty quantification for arbitrary black-box classifiers and non-i.i.d. data streams by constructing predi…
Calibrate-Then-Delegate: Safety Monitoring with Risk and Budget Guarantees via Model Cascades
Edoardo Pona, Milad Kazemi, Mehran Hosseini +4
Monitoring LLM safety at scale requires balancing cost and accuracy: a cheap latent-space probe can screen every input, but hard cases should be escalated to a more expensive exper…
Abstract Counterfactuals for Language Model Agents
Edoardo Pona, Milad Kazemi, Yali Du +2
Counterfactual inference is a powerful tool for analysing and evaluating autonomous agents, but its application to language model (LM) agents remains challenging. Existing work on…
Reinforcement Learning Fine-tuning of Language Models is Biased Towards More Extractable Features
Diogo Cruz, Edoardo Pona, Alex Holness-Tofts +4
Many capable large language models (LLMs) are developed via self-supervised pre-training followed by a reinforcement-learning fine-tuning phase, often based on human or AI feedback…