mlsanityData to 7 Oct 2026

WildReward: Learning Reward Models from In-the-Wild Human Interactions

arXiv 2602.08829 ↗First posted 9 Feb 2026cs.CL cs.AIcited by 3

On the map: LLM alignment / RLHF / preference optimisation → Reward modeling and RLHF

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 37 of its 49 references that are in the map. First posted on arXiv 9 Feb 2026.

Builds on

37 of 49 references.

Closest ancestors · 15

Same direction, newest first

  1. 2025Ask a Strong LLM Judge when Your Reward Model is Uncertain23 Oct
  2. 2025Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy2 Jul
  3. 2025HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages16 May
  4. 2025A Unified Pairwise Framework for RLHF: Bridging Generative Reward Modeling and Policy Optimization7 Apr
  5. 2025Inference-Time Scaling for Generalist Reward Modeling3 Apr
  6. 2025Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems26 Feb
  7. 2024LongReward: Improving Long-context Large Language Models with AI Feedback28 Oct
  8. 2024Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs24 Oct
  9. 2024RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style21 Oct
  10. 2024How to Evaluate Reward Models for RLHF18 Oct
  11. 2024HelpSteer2-Preference: Complementing Ratings with Preferences2 Oct
  12. 2024Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts18 Jun
3 more
  1. 2024Bayesian Reward Models for LLM Alignment20 Feb
  2. 2024ODIN: Disentangled Reward Mitigates Hacking in RLHF11 Feb
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Model29 May

Other references · 22

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2020Scaling Laws for Neural Language Modelscited by 6,411
  3. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  4. 2017On Calibration of Modern Neural Networkscited by 4,860
  5. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  6. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,758
  7. 2024Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluatorscited by 865
  8. 2024WildChat: 1M ChatGPT Interaction Logs in the Wildcited by 598
  9. 2023Prometheus: Inducing Fine-grained Evaluation Capability in Language Modelscited by 558
  10. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 550
  11. 2024From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipelinecited by 484
  12. 2024JudgeBench: A Benchmark for Evaluating LLM-based Judgescited by 294
10 more
  1. 2024LiPO: Listwise Preference Optimization through Learning-to-Rankcited by 94
  2. 2024OffsetBias: Leveraging Debiased Data for Tuning Evaluatorscited by 94
  3. 2025Infinity Instruct: Scaling Instruction Selection and Synthesis to Enhance Language Modelscited by 49
  4. 2025Reward Reasoning Modelcited by 47
  5. 2024WildFeedback: Aligning LLMs With In-situ User Interactions And Feedbackcited by 31
  6. 2024Aligning Crowd Feedback via Distributional Preference Reward Modelingcited by 26
  7. 2025User Feedback in Human-LLM Dialogues: A Lens to Understand Users But Noisy as a Learning Signalcited by 19
  8. 2023Leveraging Implicit Feedback from Deployment Data in Dialoguecited by 14
  9. 2025The Era of Real-World Human Interaction: RL from User Conversationscited by 13
  10. 2025RLMR: Reinforcement Learning with Mixed Rewards for Creative Writingcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026ThoughtTrace: Understanding User Thoughts in Real-World LLM Interactionscited by 4
  2. 2026Neglected Free Lunch from Post-training: Progress Advantage for LLM Agentscited by 2
  3. 2026Different Feedback, Different Updates: Selective Self-Learning from User Interactions for Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024RewardBench: Evaluating Reward Models for Language Modeling
  2. 2025BaseReward: A Strong Baseline for Multimodal Reward Model
  3. 2026Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization
  4. 2024RRM: Robust Reward Model Training Mitigates Reward Hacking
  5. 2024M-RewardBench: Evaluating Reward Models in Multilingual Settings
  6. 2026RMGAP: Benchmarking the Generalization of Reward Models across Diverse Preferences
  7. 2026Aligning Language Models from User Interactions
  8. 2026RewardUQ: A Unified Framework for Uncertainty-Aware Reward Models