arXiv AI
Provable Pluralistic Alignment: Multi-Party RLHF under Offline Human Feedback
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 12
Multiplayer Nash Preference Optimization
arXiv:2509. 23102v4 Announce Type: replace Abstract: Reinforcement learning from human feedback (RLHF) has emerged as the standard paradigm for aligning large language models with human preferences.
arXiv AI
Jun 2
Efficient Exploration for Iterative Nash Preference Optimization
arXiv:2606. 01382v1 Announce Type: cross Abstract: Preference alignment is central to improving large language models, but standard reward-based formulations can be restrictive when human preferences are cyclic, non-transitive, or otherwise not representable by a scalar reward.
arXiv AI
Sep 1
Personalized Group Relative Policy Optimization for Heterogenous Preference Alignment
The paper introduces Personalized Group Relative Policy Optimization (P‑GRPO), a new alignment framework for large language models that separates advantage estimation from immediate batch statistics. By normalizing advantages using preference‑group‑specific reward histories instead of the concurrent generation group, P‑GRPO maintains contrastive signals for distinct user preferences. Experiments across various tasks show that P‑GRPO converges faster and yields higher rewards than standard GRPO, improving alignment with heterogeneous human preferences while preserving general capabilities.
arXiv Machine Learning
Jun 18
When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning?
arXiv:2606. 18531v1 Announce Type: cross Abstract: Offline reinforcement learning is typically analyzed under process-level reward supervision, yet many sequential decision datasets record only trajectory-level outcomes.
arXiv Machine Learning
Sep 4
Towards Scaling Reinforcement Learning to Massive Populations: Learning Mean-Field Representations
The paper proposes a mean‑field reinforcement learning framework that models rewards and transitions as functions of an unknown low‑dimensional aggregate statistic of a large agent population. By learning this low‑dimensional representation in an offline setting, the authors demonstrate a provable method for obtaining near‑optimal policies. Experiments on a one‑step routing game inspired by supply‑chain problems show that, with a fixed neural‑network size and optimization budget, the learned representation improves reward prediction and the quality of Nash equilibria compared to baselines that ignore population structure.
arXiv AI
Aug 26
Algorithmic Impact Reveals the Hidden Social Choice Structure of Alignment
The paper reinterprets AI alignment as a social choice problem, framing it as linear optimization over a convex impact space. This approach links alignment protocols to welfare outcomes, enabling the use of welfare economics and mechanism design tools. The authors demonstrate strategyproof, unanimous mechanisms like voting-by-issues and random-dictatorship, and derive alignment protocols that maximize utilitarian welfare while respecting harm constraints, validated on real human preference data.