RLHF reward modeling satisfies pairwise majority and Condorcet consistency when each response pair is labeled once, because the maximum likelihood ranking then matches the Copeland rule.
Fundamental Limits of Game-Theoretic LLM Alignment: Smith Consistency and Preference Matching
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Nash Learning from Human Feedback is a game-theoretic framework for aligning large language models (LLMs) with human preferences by modeling learning as a two-player zero-sum game. However, using raw preference as the payoff in the game highly limits the potential of the game-theoretic LLM alignment framework. In this paper, we systematically study using what choices of payoff based on the pairwise human preferences can yield desirable alignment properties. We establish necessary and sufficient conditions for Condorcet consistency, diversity through mixed strategies, and Smith consistency. These results provide a theoretical foundation for the robustness of game-theoretic LLM alignment. Further, we show the impossibility of preference matching -- i.e., no smooth and learnable mappings of pairwise preferences can guarantee a unique Nash equilibrium that matches a target policy, even under standard assumptions like the Bradley-Terry-Luce model. This result highlights the fundamental limitation of game-theoretic LLM alignment.
citation-role summary
background 1
citation-polarity summary
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Theoretical Tensions in RLHF: Reconciling Empirical Success with Inconsistencies in Social Choice Theory
RLHF reward modeling satisfies pairwise majority and Condorcet consistency when each response pair is labeled once, because the maximum likelihood ranking then matches the Copeland rule.