Pith. sign in

REVIEW 4 cited by

Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.23630 v1 pith:4QCA2LQA submitted 2024-10-31 cs.LG cs.AI

Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI

Hadassah Harland , Richard Dazeley , Peter Vamplew , Hashini Senaratne , Bahareh Nakisa , Francisco Cruz This is my paper
classification cs.LG cs.AI
keywords alignmentapproachdiversedynamiclearningpluralisticreinforcementsystems
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Emerging research in Pluralistic Artificial Intelligence (AI) alignment seeks to address how intelligent systems can be designed and deployed in accordance with diverse human needs and values. We contribute to this pursuit with a dynamic approach for aligning AI with diverse and shifting user preferences through Multi Objective Reinforcement Learning (MORL), via post-learning policy selection adjustment. In this paper, we introduce the proposed framework for this approach, outline its anticipated advantages and assumptions, and discuss technical details about the implementation. We also examine the broader implications of adopting a retroactive alignment approach through the sociotechnical systems perspective.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback

    cs.AI 2026-07 conditional novelty 5.0

    LEMUR jointly learns a separate reward model for each teacher's preferences and uses them to train a population of multi-objective policies, beating baselines that merge feedback into one reward.

  2. Initiation Safety: A Missing Dimension in Generalist-Robot Safety

    cs.RO 2026-07 conditional novelty 5.0

    Robot safety should treat "may I start a social interaction at all" as a separate authorization layer, implemented with staged non-verbal probes and a gate before any first word or reach.

  3. Virtual Agent Economies

    cs.AI 2025-09 conditional novelty 5.0

    Proposes a two-axis framework (emergent versus intentional, permeable versus impermeable) for the coming AI agent economy and argues for proactively designing steerable agent markets.

  4. Initiation Safety: A Missing Dimension in Generalist-Robot Safety

    cs.RO 2026-07 conditional novelty 4.0

    The paper introduces initiation authorization as a distinct robot-safety layer and implements PAS, a probe-authorize-speak protocol, on a humanoid robot with a proposed three-condition user study.