ICML 2024PastSafety & alignment
ICML 2024 Workshop on Models of Human Feedback for AI Alignment
ICML 2024 Workshop MHFAIA
- Submission deadline
- Jun 1, 2024, 18:00 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (60)
Fetched from OpenReview (v2) on 2026-06-10.
"You just can’t go around killing people'' Explaining Agent Behavior to a Human Terminator
A Theoretical Framework for Partially Observed Reward-States in RLHF
Accelerating Best-of-N via Speculative Rejection
Adversarial Multi-dueling Bandits
AI Alignment with Changing and Influenceable Reward Functions
Aligning Crowd Feedback via Distributional Preference Reward Modeling
Aligning Large Language Models with Representation Editing: A Control Perspective
AMBER: An Entropy Maximizing Environment Design Algorithm for Inverse Reinforcement Learning
Beyond Thumbs Up/Down: Untangling Challenges of Fine-Grained Feedback for Text-to-Image Generation
Bootstrapping Language Models with DPO Implicit Rewards
Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization
Comparing Comparisons: Informative and Easy Human Feedback with Distinguishability Queries
Concept-Based Interpretable Reinforcement Learning with Limited to No Human Labels
Cross-Domain Knowledge Transfer for RL via Preference Consistency
Distributional Preference Alignment of LLMs via Optimal Transport
DPM: Dual Preferences-based Multi-Agent Reinforcement Learning
DPO Meets PPO: Reinforced Token Optimization for RLHF
Efficient Inverse Reinforcement Learning without Compounding Errors
Enhancing Intent Understanding for Ambiguous prompt: A Human-Machine Co-Adaption Strategy
Filtered Direct Preference Optimization
Free-Energy Equilibria: Toward a Theory of Interactions Between Boundedly-Rational Agents
Generalizing Offline Alignment Theoretical Paradigm with Diverse Divergence Constraints
Hummer: Towards Limited Competitive Preference Dataset
Informed Meta-Learning
Inverse Reinforcement Learning from Demonstrations for LLM Alignment
Is a Good Description Worth a Thousand Pictures? Reducing Multimodal Alignment to Text-Based, Unimodal Alignment
Is poisoning a real threat to LLM alignment? Maybe more so than you think
Language Alignment via Nash-learning and Adaptive feedback
Learning the eye of the beholder: Statistical modeling and estimation for personalized color perception
Learning to Assist Humans without Inferring Rewards
MaxMin-RLHF: Towards Equitable Alignment of Large Language Models with Diverse Human Preferences
Modeling the Plurality of Human Preferences via Ideal Points
Models That Prove Their Own Correctness
Multi-Agent Imitation Learning: Value is Easy, Regret is Hard
MultiScale Policy Learning for Alignment with Long Term Objectives
New Desiderata for Direct Preference Optimization
Off-Policy Evaluation from Logged Human Feedback
Optimal Design for Human Feedback
Order-Optimal Instance-Dependent Bounds for Offline Reinforcement Learning with Preference Feedback
PIPER: Primitive-Informed Preference-based Hierarchical Reinforcement Learning via Hindsight Relabeling
Preference Elicitation for Offline Reinforcement Learning
Preference Learning Algorithms Do Not Learn Preference Rankings
Prompt Optimization with Human Feedback
Query Design for Crowdsourced Clustering: Effect of Cognitive Overload and Contextual Bias
REBEL: Reinforcement Learning via Regressing Relative Rewards
Regularized Best-of-N Sampling to Mitigate Reward Hacking for Language Model Alignment
Reinforcement Learning from Human Text Feedback: Learning a Reward Model from Human Text Input
Relatively Rational: Learning Utilities and Rationalities Jointly from Pairwise Preferences
Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment
Revisiting Successor Features for Inverse Reinforcement Learning
RLHF and IIA: Perverse Incentives
Scalable Oversight by Accounting for Unreliable Feedback
Scalably Solving Assistance Games
Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms
Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrapping
Stochastic Concept Bottleneck Models
Towards Aligning Language Models with Textual Feedback
Towards Safe Large Language Models for Medicine
Uncertainty-aware Preference Alignment in Reinforcement Learning from Human Feedback
Weak-to-Strong Extrapolation Expedites Alignment