Assistive Dueling Bandits: No-Regret Algorithms for Assisting No-Regret Users

Mark Bedaywi, Cassidy Laidlaw, Austin Tripp, Nika Haghtalab

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs

MOOD benchmark shows guard models fail to detect out-of-distribution alignment failures, but combining them with Mahalanobis and perplexity detectors improves recall from 39% to 45% and scales positively.

Dylan Feng, Pragya Srivastava, Anca Dragan, Cassidy Laidlaw

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Training Language Models to Explain Their Own Computations

Fine-tuning language models on interpretability ground truth teaches them to describe their internal computations, with self-explanation outperforming larger external explainers.

Belinda Z Li, Zifan Carl Guo, Vincent Huang, Jacob Steinhardt and 1 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 1 on Hugging Face · Code ★ 38

Predictive Concept Decoders: Training Scalable End-to-End Interpretability Assistants

Predictive Concept Decoders train end-to-end interpretability assistants that encode neural activations into sparse concepts to predict model behavior, scaling with data to detect jailbreaks, hidden hints, and latent attributes.

Vincent Huang, Dami Choi, Daniel D Johnson, Sarah Schwettmann and 1 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026