Cover Image

COPR: Continual Human Preference Learning via Optimal Policy Regularization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Han, Gui, Lin, Lei, Yu, Zhai, Yuanzhao, Zhang, Yehong, He, Yulan, Wang, Hui, Yu, Yue, Wong, Kam-Fai, Liang, Bin, Xu, Ruifeng
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

COPR: Continual Learning Human Preference through Optimal Policy Regularization
by: Zhang, Han, et al.
Published: (2023)

Correcting Large Language Model Behavior via Influence Function
by: Zhang, Han, et al.
Published: (2024)

Multi-modal Stance Detection: New Datasets and Model
by: Liang, Bin, et al.
Published: (2024)

Mitigating Biases of Large Language Models in Stance Detection with Counterfactual Augmented Calibration
by: Li, Ang, et al.
Published: (2024)

Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles
by: Zhai, Yuanzhao, et al.
Published: (2023)

ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuning
by: Du, Yiming, et al.
Published: (2025)

WHERE and WHICH: Iterative Debate for Biomedical Synthetic Data Augmentation
by: Zhao, Zhengyi, et al.
Published: (2025)

MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents
by: Du, Yiming, et al.
Published: (2025)

Online Self-Preferring Language Models
by: Zhai, Yuanzhao, et al.
Published: (2024)

EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-Forget
by: Chen, Liang, et al.
Published: (2025)

OSPC: Detecting Harmful Memes with Large Language Model as a Catalyst
by: Cao, Jingtao, et al.
Published: (2024)

FReM: A Flexible Reasoning Mechanism for Balancing Quick and Slow Thinking in Long-Context Question Answering
by: Zhao, Zhengyi, et al.
Published: (2025)

Counterspeech for Mitigating the Influence of Media Bias: Comparing Human and LLM-Generated Responses
by: Lin, Luyang, et al.
Published: (2025)

Investigating Bias in LLM-Based Bias Detection: Disparities between LLMs and Human Perception
by: Lin, Luyang, et al.
Published: (2024)

COPR -- Efficient, large-scale log storage and retrieval
by: Reichinger, Julian, et al.
Published: (2024)

Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning
by: Chen, Liang, et al.
Published: (2025)

Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning
by: Chen, Liang, et al.
Published: (2025)

Shaping the Anthropocene: Understanding and Evaluating Human Impact on the Global Ecosystem
by: Yuanzhao Ding
Published: (2025)

Reply with Sticker: New Dataset and Model for Sticker Retrieval
by: Liang, Bin, et al.
Published: (2024)

PEARL: Towards Permutation-Resilient LLMs
by: Chen, Liang, et al.
Published: (2025)

SymbolicThought: Integrating Language Models and Symbolic Reasoning for Consistent and Interpretable Human Relationship Understanding
by: Zhao, Runcong, et al.
Published: (2025)

Nonlinear optical analogues of quantum phase transitions in a squeezing-enhanced LMG model
by: Kam, Chon-Fai
Published: (2025)

Majorana Constellations: A Geometric Lens on Multipartite Entanglement and Geometric Phases
by: Kam, Chon-Fai
Published: (2026)

Three-Axis Spin Squeezed States Associated with Excited-State Quantum Phase Transitions
by: Kam, Chon-Fai
Published: (2025)

Nonlinear optical realization of non-integrable phases accompanying quantum phase transitions
by: Kam, Chon-Fai
Published: (2025)

VLEU: a Method for Automatic Evaluation for Generalizability of Text-to-Image Models
by: Cao, Jingtao, et al.
Published: (2024)

Towards Real-World Stickers Use: A New Dataset for Multi-Tag Sticker Recognition
by: Wang, Bingbing, et al.
Published: (2024)

Model Provenance via Model DNA
by: Mu, Xin, et al.
Published: (2023)

Enhancing Large Language Models Against Inductive Instructions with Dual-critique Prompting
by: Wang, Rui, et al.
Published: (2023)

CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility
by: Zi, Bojia, et al.
Published: (2024)

Reality Copilot: Voice-First Human-AI Collaboration in Mixed Reality Using Large Multimodal Models
by: Yu, Liuchuan, et al.
Published: (2026)

EventWeave: A Dynamic Framework for Capturing Core and Supporting Events in Dialogue Systems
by: Zhao, Zhengyi, et al.
Published: (2025)

Role Prompting Guided Domain Adaptation with General Capability Preserve for Large Language Models
by: Wang, Rui, et al.
Published: (2024)

From Prediction to Justification: Aligning Sentiment Reasoning with Human Rationale via Reinforcement Learning
by: Zhang, Shihao, et al.
Published: (2026)

Multi-Layer Ranking with Large Language Models for News Source Recommendation
by: Zhang, Wenjia, et al.
Published: (2024)

Dual-Density Inference for Efficient Language Model Reasoning
by: Zhao, Zhengyi, et al.
Published: (2025)

Analytical approximations for generalized quantum Rabi models
by: Kam, Chon-Fai, et al.
Published: (2024)

Sub-microsecond high-fidelity dispersive readout of a spin qubit with squeezed photons
by: Kam, Chon-Fai, et al.
Published: (2023)

Super-Poissonian Squeezed Light in the Deep Strong Regime of the Quantum Rabi Model
by: Kam, Chon-Fai, et al.
Published: (2024)

Fast and high-fidelity dispersive readout of a spin qubit via squeezing and resonator nonlinearity
by: Kam, Chon-Fai, et al.
Published: (2024)