Author

Amin Memarian

h-index 1 View on Semantic Scholar

We have 2 of 5 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.

Preprint Aug 2026

Evaluation Awareness in Language Models: Representation, Verbalization, and Control

Results show the need for evaluations to account for the disjunction between what models represent internally, what they verbalize, and their steering, and the need for evaluations to account for the disjunction between what models represent internally, what they verbalize, and their steering.

Farzaneh Heidari, Amin Memarian, Guillaume Rabusseau · 2 citations

#artificial intelligence Preprint May 2026

Position: Collusion Risks Among AI Reasoning Agents Justify Certification Requirements for Making Market Decisions

This position paper argues that AI agents with chain-of-thought reasoning capabilities are predisposed to exhibit collusive behavior and should be required to obtain behavioral certification before making decisions that affect economic markets, and provides preliminary evidence that such agents can be steered in a gene...

Matthew Riemer, Tommaso Tosato, Amin Memarian et al. · 0 citations