WildReward: Learning Reward Models from In-the-Wild Human Interactions
Abstract
WildReward demonstrates that reward models can be effectively trained from in-the-wild user interactions using ordinal regression, achieving performance comparable to traditional methods while benefiting from user diversity.
Reward models (RMs) are crucial for the training of large language models (LLMs), yet they typically rely on large-scale human-annotated preference pairs. With the widespread deployment of LLMs, in-the-wild interactions have emerged as a rich source of implicit reward signals. This raises the question: Can we develop reward models directly from in-the-wild interactions? In this work, we explore this possibility by adopting WildChat as an interaction source and proposing a pipeline to extract reliable human feedback, yielding 186k high-quality instances for training WildReward via ordinal regression directly on user feedback without preference pairs. Extensive experiments demonstrate that WildReward achieves comparable or even superior performance compared to conventional reward models, with improved calibration and cross-sample consistency. We also observe that WildReward benefits directly from user diversity, where more users yield stronger reward models. Finally, we apply WildReward to online DPO training and observe significant improvements across various tasks. Code and data are released at https://github.com/THU-KEG/WildReward.
Community
This paper explores training reward models from in-the-wild human interactions.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- CE-RM: A Pointwise Generative Reward Model Optimized via Two-Stage Rollout and Unified Criteria (2026)
- Reward Modeling from Natural Language Human Feedback (2026)
- RM-Distiller: Exploiting Generative LLM for Reward Model Distillation (2026)
- R-Align: Enhancing Generative Reward Models through Rationale-Centric Meta-Judging (2026)
- IRPM: Intergroup Relative Preference Modeling for Pointwise Generative Reward Models (2026)
- From Absolute to Relative: Rethinking Reward Shaping in Group-Based Reinforcement Learning (2026)
- AdaJudge: Adaptive Multi-Perspective Judging for Reward Modeling (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper