arXiv AI
Axiom Satisfiability of Linear Rewards in Alignment
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
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.
arXiv AI
Jul 24
Towards Disentangled Preference Optimization Dynamics: Suppress the Loser, Preserve the Winner
arXiv:2604. 18239v4 Announce Type: replace-cross Abstract: Preference optimization is widely used to align large language models (LLMs) with human preferences.
arXiv Machine Learning
Aug 10
Multiscale Reward Hedging from Correct Demonstrations
arXiv:2608. 06825v1 Announce Type: new Abstract: Learning from correct demonstrations is harder than supervised learning when many answers are correct: after predicting, the learner sees one valid answer but not whether its own answer was valid, nor any reward.
arXiv Machine Learning
Sep 4
EF1-Constrained Nash Social Welfare with Identical Additive Valuations: Complexity, Guarantees, and Experiments
arXiv:2609. 03846v1 Announce Type: cross Abstract: We study the allocation of indivisible goods among agents with identical additive valuations, focusing on envy-freeness up to one good (EF1) and Nash social welfare (NSW).
arXiv Machine Learning
Aug 20
Sharp Capacity Thresholds in Linear Associative Memory: From Top-1 Retrieval to Tail-Average Learning
arXiv:2605. 05189v2 Announce Type: replace-cross Abstract: How many key-value associations can a $d\times d$ linear memory store?
arXiv Machine Learning
Aug 13
A Framework for Designing Reward Functions: From Objectives to Features to Human-Aligned Reward Functions
arXiv:2608. 12302v1 Announce Type: new Abstract: We present a formal process to enable non-experts to instantiate and iterate on human-aligned reward functions, i.