conftrace_

reinforcement learning from human feedback

278 papers

Explore in graph

Co-occurring keywords

large language model (13587) reward model (276) reinforcement learning (4352) direct preference optimization (332) language model alignment (142) reward modeling (164) human feedback (161) preference learning (418) model alignment (226) language model (4599)

Papers

Increasing the Difficulty of Automatically Generated Questions via Reinforcement Learning with Synthetic Preference for Cost-Effective Cultural Heritage Dataset Generation EMNLP 2024
Policy Evaluation for Reinforcement Learning from Human Feedback: A Sample Complexity Analysis AISTATS 2024
Would I Lie To You? Inference Time Alignment of Language Models using Direct Preference Heads NIPS 2024
DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation NIPS 2024
Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence EMNLP 2024
Rich Human Feedback for Text-to-Image Generation CVPR 2024
Alignment at Pre-training! Towards Native Alignment for Arabic LLMs NIPS 2024
UltraMedical: Building Specialized Generalists in Biomedicine NIPS 2024
Perplexity-aware Correction for Robust Alignment with Noisy Preferences NIPS 2024
Mission Impossible: A Statistical Perspective on Jailbreaking LLMs NIPS 2024
Geometric-Averaged Preference Optimization for Soft Preference Labels NIPS 2024
RA-PbRL: Provably Efficient Risk-Aware Preference-Based Reinforcement Learning NIPS 2024
Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs NIPS 2024
Self-Play Fine-tuning of Diffusion Models for Text-to-image Generation NIPS 2024
Axioms for AI Alignment from Human Feedback NIPS 2024
Online Iterative Reinforcement Learning from Human Feedback with General Preference Model NIPS 2024
Aligner: Efficient Alignment by Learning to Correct NIPS 2024
When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback NIPS 2024
Improving Summarization with Human Edits EMNLP 2023
Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback EMNLP 2023
Large Language Models are biased to overestimate profoundness EMNLP 2023
Axiomatic Preference Modeling for Longform Question Answering EMNLP 2023
Self-Criticism: Aligning Large Language Models with their Understanding of Helpfulness, Honesty, and Harmlessness EMNLP 2023
RRHF: Rank Responses to Align Language Models with Human Feedback NIPS 2023
Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery NIPS 2023