Research map / Reinforcement learning / RL from feedback
SharedRep-RLHF: A Shared Representation Approach to RLHF with Diverse Preferences
Arpan Mukherjee, Marcello Bullo, Deniz Gündüz
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace group-specific reward models with shared representation (SharedRep-RLHF) | MaxMin-RLHF · IMDb sentiment, minority 1% | mean minority score: 0.59 -> 0.69 | Improved |
| replace group-specific reward models with shared representation | MaxMin-RLHF · IMDb sentiment (1% to 20% minority) | minority win rate: 21.38 -> 25.26 (1%) | Improved |
| replace group-specific reward models with shared representation | MaxMin-RLHF · GSM8K preference, minority 5% | mean minority score: 0.14 -> 0.29 | Improved |
| replace group-specific reward models with shared representation | MaxMin-RLHF · GSM8K preference, minority 5% | minority win rate: 4.93 -> 25.32 | Improved |
| replace group-specific reward models with shared representation | MaxMin-RLHF · GSM8K preference, minority 30% | mean minority score: 0.30 -> 0.27 | Hurt |
| replace group-specific reward models with shared representation | MaxMin-RLHF · GSM8K preference, minority 30% | minority win rate: 31.65 -> 22.76 | Hurt |
| replace group-specific reward models with shared representation | MaxMin-RLHF · GSM8K preference (all minority proportions) | mean minority score | Mixed |
Closest papers by meaning
- MaxMin-RLHF: Alignment with Diverse Human Preferences (ICML 2024 · similarity 0.92)
- Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning (NeurIPS 2024 · similarity 0.92)
- Nash Learning from Human Feedback (ICML 2024 · similarity 0.90)
- Provably Efficient Online RLHF with One-Pass Reward Modeling (NeurIPS 2025 · similarity 0.90)
- How to Evaluate Reward Models for RLHF (ICLR 2025 · similarity 0.90)
- Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF (ICLR 2024 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
