arXiv AI August 6, 2026 By Isaiah Andrews

Revealed Rationality: Label-Free Evaluation and Regularization from Representation Theorems

arXiv:2608. 05015v1 Announce Type: cross Abstract: Representation theorems in decision theory establish that behavior satisfies certain axioms if and only if it can be rationalized by a well-defined objective.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

llms

arXiv AI

Jun 30

Geometric Measurements of the Axiom of Choice in Neural Proof Embeddings

arXiv:2606. 28572v1 Announce Type: cross Abstract: The axiom of choice has divided the foundations of mathematics for over a century, but the distinction between classical and constructive proofs has remained a philosophical and methodological one.

By Rodrigo Mendoza-Smith

rag

arXiv Machine Learning

Jun 2

The Representation-Rationalizability Tradeoff in Reward Learning

arXiv:2606. 00291v1 Announce Type: cross Abstract: In RLHF, each training example contains a prompt $x$ and two candidate responses $y,y'$, and annotators provide pairwise preferences between these responses.

By Jing Dong, Yaoliang Yu, Pascal Pourpart

rag reinforcement-learning

arXiv AI

Jun 15

Flood and Harvest: The Provable Necessity of Trivia for Generating Valuable Mathematics via the Lens of Language Generation in the Limit

arXiv:2606. 14688v1 Announce Type: cross Abstract: AI systems coupled to proof assistants now generate formal mathematics at scale, and the gap between what a checker can verify and what a mathematician would value has become the binding constraint.

By Xiaoyu Li, Andi Han, Dai Shi, Zheng Gao, Jiaojiao Jiang, Junbin Gao

safety

arXiv Statistics ML

Sep 10

A Unifying Perspective on Probabilities as Model Predictions

arXiv:2609.09855v1 Announce Type: new Abstract: Although probabilistic statements are ubiquitous, foundational disagreements persist about their understanding, as exemplified by debates between Bayes...

By Benedikt H\"oltgen

arXiv AI

Jun 24

When Preferences Fail to Become Incentives: A Utility-Behavior Gap in Large Language Models

arXiv:2606. 22974v2 Announce Type: replace Abstract: Recent work on preference elicitation in large language models (LLMs) has demonstrated that, when given a series of choices between two outcomes, LLMs reveal a coherent, model-specific utility structure.

By Yujun Zhou, Christopher M. Ackerman

llms safety

arXiv Machine Learning

Sep 15

Unfair Utilities and First Steps Towards Improving Them

arXiv:2306.00636v3 Announce Type: replace-cross Abstract: Many fairness criteria constrain the policy or choice of predictors, which can have unwanted consequences, in particular, when optimizing the...

By Frederik Hytting J{\o}rgensen, Sebastian Weichwald, Jonas Peters

safety

One email a morning, machine-written

Related stories

Geometric Measurements of the Axiom of Choice in Neural Proof Embeddings

The Representation-Rationalizability Tradeoff in Reward Learning

Flood and Harvest: The Provable Necessity of Trivia for Generating Valuable Mathematics via the Lens of Language Generation in the Limit

A Unifying Perspective on Probabilities as Model Predictions

When Preferences Fail to Become Incentives: A Utility-Behavior Gap in Large Language Models

Unfair Utilities and First Steps Towards Improving Them