Author

Arthur Conmy

h-index 4 View on Semantic Scholar

We have 2 of 11 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Mar 2026

How do LLMs Compute Verbal Confidence

It is demonstrated that verbal confidence reflects automatic, sophisticated self-evaluation -- not post-hoc reconstruction -- with implications for understanding metacognition in LLMs and improving calibration.

D. Kumaran, Arthur Conmy, Federico Barbero et al. · arXiv.org · 21 citations · ⚡1

#artificial intelligence Jun 2026

How Transparent is DiffusionGemma?

A suite of interpretability case studies are conducted, uncovering initial evidence of novel diffusion-specific phenomena such as non-chronological reasoning, token and sequence smearing, and intermediate-context reasoning, and monitorability is found, which finds that DiffusionGemma is similarly monitorable to Gemma 4...

Joshua Engels, C. McDougall, Bilal Chughtai et al. · arXiv.org · 1 citation