arXiv Machine Learning
Should I stay or should I show? Learning to selectively disclose information
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jun 8
Off-Policy Evaluation with Strategic Agents via Local Disclosure
arXiv:2606. 07308v1 Announce Type: new Abstract: We study off-policy evaluation (OPE) under strategic behavior where decision subjects (or agents) respond to a decision maker's policy by strategically modifying their covariates.
arXiv Computation and Language
Aug 25
Expectations and Practices around AI Disclosure in CS Research
The paper examines AI disclosure policies in top computer science venues, finding them to be highly under‑specified. A survey of 109 researchers shows that disclosures are deemed most necessary for research design tasks and when human involvement is low, and it compiles researchers’ expectations for disclosure content. Analysis of 13,867 disclosure statements from EMNLP 2025 and ICLR 2026 reveals a significant mismatch between these expectations and actual practice, such as frequent disclosure of writing assistance despite it being considered less necessary.
Hugging Face Trending Papers
Aug 24
Expectations and Practices around AI Disclosure in CS Research
As generative AI tools find increasing use in research workflows, ongoing debates on their impact, appropriateness and responsible use have led policymakers to enact policies to disclose AI use at mul...
arXiv Machine Learning
Jun 10
Ambiguous Strategic Classification
arXiv:2606. 10137v1 Announce Type: new Abstract: A common assumption in strategic classification is that the classifier is public knowledge.
arXiv AI
Jun 30
Safety from Honesty in a Disinterested AI Predictor
arXiv:2606. 29657v1 Announce Type: new Abstract: As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified.
Hugging Face Trending Papers
Jun 28
Safety from Honesty in a Disinterested AI Predictor
As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified. We present a formal safety argument for the Scientist AI (SAI) Predictor, trained to approximate the Bayesian posterior conditioned on a dataset of "epistemically contextualized" natural-language statements.