Miles Turpin — accepted AI-conference papers

2025

Looking Inward: Language Models Can Learn About Themselves by Introspection

Felix Jedidja Binder, James Chua, Tomek Korbak, Henry Sleight, John Hughes, Robert Long +3

ICLR 2025poster

Humans acquire knowledge by observing the external world, but also by introspection. Introspection gives a person privileged access to their current state of mind (e.g. thoughts and feelings) that are not accessible to external observers. Do LLMs have this introspective capability of privileged acce…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗

2023

Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting

Miles Turpin, Julian Michael, Ethan Perez, Samuel R. Bowman

NeurIPS 2023poster

Large Language Models (LLMs) can achieve strong performance on many tasks by producing step-by-step reasoning before giving a final output, often referred to as chain-of-thought reasoning (CoT). It is tempting to interpret these CoT explanations as the LLM's process for solving a task. This level of…

Cited by 410 Source ↗PDF ↗code ↗Scholar ↗