conftrace_

language model alignment

142 papers

Explore in graph

Co-occurring keywords

large language model (13587) reinforcement learning from human feedback (278) direct preference optimization (332) reinforcement learning (4352) preference learning (418) reward model (276) preference optimization (302) model alignment (226) reward modeling (164) language model (4599)

Papers

AMaPO: Adaptive Margin-attached Preference Optimization for Language Model Alignment AAAI 2026
Conformal Feedback Alignment: Quantifying Answer-Level Reliability for Robust LLM Alignment EACL 2026
Probing Preference Representations: A Multi-Dimensional Evaluation and Analysis Method for Reward Models AAAI 2026
MoralReason: Generalizable Moral Decision Alignment for LLM Agents Using Reasoning-Level Reinforcement Learning AAAI 2026
Bootstrapping LLMs via Preference-Based Policy Optimization AAAI 2026
Causal Direct Preference Optimization for Language Model Alignment EACL 2026
CTPD: Cross Tokenizer Preference Distillation AAAI 2026
RMO: Towards Better LLM Alignment via Reshaping Reward Margin Distributions AAAI 2026
Adaptive KL Control for Direct Preference Optimization in Instruction-Following LLMs AAAI 2026
ALPHA: Action-Based Learning for Pluralistic Human Alignment in Large Language Models AAAI 2026
Reducing the Scope of Language Models AAAI 2026
Textual Self-Attention Network: Test-Time Preference Optimization Through Textual Gradient-Based Attention AAAI 2026
DCRM: A Heuristic to Measure Response Pair Quality in Preference Optimization EMNLP 2025
Token-Level Accept or Reject: A Micro Alignment Approach for Large Language Models IJCAI 2025
PERSONA: A Reproducible Testbed for Pluralistic Alignment COLING 2025
Beyond Online Sampling: Bridging Offline-to-Online Alignment via Dynamic Data Transformation for LLMs EMNLP 2025
Reward Model Perspectives: Whose Opinions Do Reward Models Reward? EMNLP 2025
InsBank: Evolving Instruction Subset for Ongoing Alignment EMNLP 2025
Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignment NAACL 2025
MPPO: Multi Pair-wise Preference Optimization for LLMs with Arbitrary Negative Samples COLING 2025
Aligning Language Models Using Follow-up Likelihood as Reward Signal AAAI 2025
Anak Baik: A Low-Cost Approach to Curate Indonesian Ethical and Unethical Instructions COLING 2025
Aligning to Constraints for Data-Efficient Language Model Customization NAACL 2025
From Outcomes to Processes: Guiding PRM Learning from ORM for Inference-Time Alignment ACL 2025
Preference-Oriented Supervised Fine-Tuning: Favoring Target Model over Aligned Large Language Models AAAI 2025