pith. sign in

Interpretable preferences via multi-objective reward modeling and mixture-of-experts

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.AI 1 cs.GT 1

years

2026 1 2025 1

verdicts

UNVERDICTED 2

representative citing papers

Multiplayer Nash Preference Optimization

cs.AI · 2025-09-27 · unverdicted · novelty 6.0

MNPO extends NLHF to multiplayer Nash games, inheriting equilibrium guarantees while showing empirical gains on instruction-following benchmarks under diverse preferences.

citing papers explorer

Showing 2 of 2 citing papers.

  • Common-agency Games for Multi-Objective Test-Time Alignment cs.GT · 2026-05-08 · unverdicted · none · ref 81

    CAGE uses common-agency games and an EPEC algorithm to compute equilibrium policies that balance multiple conflicting objectives for test-time LLM alignment.

  • Multiplayer Nash Preference Optimization cs.AI · 2025-09-27 · unverdicted · none · ref 30

    MNPO extends NLHF to multiplayer Nash games, inheriting equilibrium guarantees while showing empirical gains on instruction-following benchmarks under diverse preferences.