Axioms for AI Alignment from Human Feedback

• URL: http://arxiv.org/abs/2405.14758v2
• Date: Thu, 07 Nov 2024 15:40:25 GMT
• Title: Axioms for AI Alignment from Human Feedback
• Authors: Luise Ge, Daniel Halpern, Evi Micha, Ariel D. Procaccia, Itai Shapira, Yevgeniy Vorobeychik, Junlin Wu,
• Abstract summary: We develop novel rules for learning reward functions with strong axiomatic guarantees. A key innovation from the standpoint of social choice is that our problem has a linear structure.
• Score: 44.51306968484829
• License:
• Abstract: In the context of reinforcement learning from human feedback (RLHF), the reward function is generally derived from maximum likelihood estimation of a random utility model based on pairwise comparisons made by humans. The problem of learning a reward function is one of preference aggregation that, we argue, largely falls within the scope of social choice theory. From this perspective, we can evaluate different aggregation methods via established axioms, examining whether these methods meet or fail well-known standards. We demonstrate that both the Bradley-Terry-Luce Model and its broad generalizations fail to meet basic axioms. In response, we develop novel rules for learning reward functions with strong axiomatic guarantees. A key innovation from the standpoint of social choice is that our problem has a linear structure, which greatly restricts the space of feasible rules and leads to a new paradigm that we call linear social choice.

Related papers

• Intuitions of Compromise: Utilitarianism vs. Contractualism [42.3322948655612]
  We use a paradigm that applies algorithms to aggregating preferences across groups in a social decision-making context. While the dominant approach to value aggregation up to now has been utilitarian, we find that people strongly prefer the aggregations recommended by the contractualist algorithm.
  arXiv  Detail & Related papers  (2024-10-07T21:05:57Z)
• Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning [12.742158403867002]
  Reinforcement Learning from Human Feedback is a powerful paradigm for aligning foundation models to human values and preferences. Current RLHF techniques cannot account for the naturally occurring differences in individual human preferences across a diverse population. We develop a class of multimodal RLHF methods to address the need for pluralistic alignment.
  arXiv  Detail & Related papers  (2024-08-19T15:18:30Z)
• RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation [24.374185140811115]
  Reinforcement learning from human feedback (RLHF) has been an effective technique for aligning AI systems with human values. In this paper, we focus on addressing the issues due to the inherent heterogeneity in human preferences, as well as their potential strategic behavior in providing feedback. We propose two frameworks to address heterogeneous human feedback in principled ways: personalization-based one and aggregation-based one.
  arXiv  Detail & Related papers  (2024-04-30T23:57:23Z)
• A Minimaximalist Approach to Reinforcement Learning from Human Feedback [49.45285664482369]
  We present Self-Play Preference Optimization (SPO), an algorithm for reinforcement learning from human feedback. Our approach is minimalist in that it does not require training a reward model nor unstable adversarial training. We demonstrate that on a suite of continuous control tasks, we are able to learn significantly more efficiently than reward-model based approaches.
  arXiv  Detail & Related papers  (2024-01-08T17:55:02Z)
• Nash Learning from Human Feedback [86.09617990412941]
  We introduce an alternative pipeline for the fine-tuning of large language models using pairwise human feedback. We term this approach Nash learning from human feedback (NLHF) We present a novel algorithmic solution, Nash-MD, founded on the principles of mirror descent.
  arXiv  Detail & Related papers  (2023-12-01T19:26:23Z)
• Contrastive Preference Learning: Learning from Human Feedback without RL [71.77024922527642]
  We introduce Contrastive Preference Learning (CPL), an algorithm for learning optimal policies from preferences without learning reward functions. CPL is fully off-policy, uses only a simple contrastive objective, and can be applied to arbitrary MDPs.
  arXiv  Detail & Related papers  (2023-10-20T16:37:56Z)
• Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems [82.92678837778358]
  preference-based methods have demonstrated substantial success in empirical applications such as InstructGPT. We show how human bias and uncertainty in feedback modelings can affect the theoretical guarantees of these approaches.
  arXiv  Detail & Related papers  (2023-07-24T17:50:24Z)
• Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons [79.98542868281473]
  We provide a theoretical framework for Reinforcement Learning with Human Feedback (RLHF) We show that when training a policy based on the learned reward model, MLE fails while a pessimistic MLE provides policies with improved performance under certain coverage assumptions.
  arXiv  Detail & Related papers  (2023-01-26T18:07:21Z)
• Risk Measures and Upper Probabilities: Coherence and Stratification [7.88657961743755]
  We look at richer alternatives to classical probability theory as a mathematical foundation for machine learning. We examine a powerful and rich class of alternative aggregation functionals, known variously as spectral risk measures, Choquet integrals or Lorentz norms. We empirically demonstrate how this new approach to uncertainty helps tackling practical machine learning problems.
  arXiv  Detail & Related papers  (2022-06-07T11:08:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.