From Demonstrations to Rewards: Alignment Without Explicit Human Preferences

• URL: http://arxiv.org/abs/2503.13538v1
• Date: Sat, 15 Mar 2025 20:53:46 GMT
• Title: From Demonstrations to Rewards: Alignment Without Explicit Human Preferences
• Authors: Siliang Zeng, Yao Liu, Huzefa Rangwala, George Karypis, Mingyi Hong, Rasool Fakoor,
• Abstract summary: In this paper, we propose a fresh perspective on learning alignment based on inverse reinforcement learning principles.<n>Instead of relying on large preference data, we directly learn the reward model from demonstration data.
• Score: 55.988923803469305
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: One of the challenges of aligning large models with human preferences lies in both the data requirements and the technical complexities of current approaches. Predominant methods, such as RLHF, involve multiple steps, each demanding distinct types of data, including demonstration data and preference data. In RLHF, human preferences are typically modeled through a reward model, which serves as a proxy to guide policy learning during the reinforcement learning stage, ultimately producing a policy aligned with human preferences. However, in this paper, we propose a fresh perspective on learning alignment based on inverse reinforcement learning principles, where the optimal policy is still derived from reward maximization. However, instead of relying on preference data, we directly learn the reward model from demonstration data. This new formulation offers the flexibility to be applied even when only demonstration data is available, a capability that current RLHF methods lack, and it also shows that demonstration data offers more utility than what conventional wisdom suggests. Our extensive evaluation, based on public reward benchmark, HuggingFace Open LLM Leaderboard and MT-Bench, demonstrates that our approach compares favorably to state-of-the-art methods that rely solely on demonstration data.

Related papers

• PILAF: Optimal Human Preference Sampling for Reward Modeling [14.336058926701432]
  We propose Policy-Interpolated Learning for Aligned Feedback (PILAF), a novel response sampling strategy for preference labeling.<n>PILAF explicitly aligns preference learning with maximizing the underlying oracle reward.
  arXiv  Detail & Related papers  (2025-02-06T18:09:00Z)
• Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment [65.15914284008973]
  We propose to leverage an Inverse Reinforcement Learning (IRL) technique to simultaneously build an reward model and a policy model. We show that the proposed algorithms converge to the stationary solutions of the IRL problem. Our results indicate that it is beneficial to leverage reward learning throughout the entire alignment process.
  arXiv  Detail & Related papers  (2024-05-28T07:11:05Z)
• Inverse-RLignment: Large Language Model Alignment from Demonstrations through Inverse Reinforcement Learning [62.05713042908654]
  We introduce Alignment from Demonstrations (AfD), a novel approach leveraging high-quality demonstration data to overcome these challenges.<n>We formalize AfD within a sequential decision-making framework, highlighting its unique challenge of missing reward signals.<n> Practically, we propose a computationally efficient algorithm that extrapolates over a tailored reward model for AfD.
  arXiv  Detail & Related papers  (2024-05-24T15:13:53Z)
• Fine-Tuning Language Models with Reward Learning on Policy [68.70065254564642]
  Reinforcement learning from human feedback (RLHF) has emerged as an effective approach to aligning large language models (LLMs) to human preferences. Despite its popularity, (fixed) reward models may suffer from inaccurate off-distribution. We propose reward learning on policy (RLP), an unsupervised framework that refines a reward model using policy samples to keep it on-distribution.
  arXiv  Detail & Related papers  (2024-03-28T10:02:10Z)
• Secrets of RLHF in Large Language Models Part II: Reward Modeling [134.97964938009588]
  We introduce a series of novel methods to mitigate the influence of incorrect and ambiguous preferences in the dataset. We also introduce contrastive learning to enhance the ability of reward models to distinguish between chosen and rejected responses.
  arXiv  Detail & Related papers  (2024-01-11T17:56:59Z)
• ULMA: Unified Language Model Alignment with Human Demonstration and Point-wise Preference [16.73260713938154]
  A typical alignment procedure consists of supervised fine-tuning and preference learning. We introduce Point-wise Direct Preference Optimization, a novel preference learning method designed to harness point-wise feedback effectively. Our work also uncovers a novel connection between supervised fine-tuning and point-wise preference learning, culminating in Unified Language Model Alignment.
  arXiv  Detail & Related papers  (2023-12-05T07:52:12Z)
• Pre-trained Recommender Systems: A Causal Debiasing Perspective [19.712997823535066]
  We develop a generic recommender that captures universal interaction patterns by training on generic user-item interaction data extracted from different domains. Our empirical studies show that the proposed model could significantly improve the recommendation performance in zero- and few-shot learning settings.
  arXiv  Detail & Related papers  (2023-10-30T03:37:32Z)
• S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization [104.87483578308526]
  We propose the model S3-Rec, which stands for Self-Supervised learning for Sequential Recommendation. For our task, we devise four auxiliary self-supervised objectives to learn the correlations among attribute, item, subsequence, and sequence. Extensive experiments conducted on six real-world datasets demonstrate the superiority of our proposed method over existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-08-18T11:44:10Z)

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.