Buchumschlag

RULE: Reinforcement UnLEarning Achieves Forget-Retain Pareto Optimality

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Zhang, Chenlong, Jin, Zhuoran, Yuan, Hongbang, Wei, Jiaheng, Zhou, Tong, Liu, Kang, Zhao, Jun, Chen, Yubo
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Computation and Language Machine Learning
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Beyond Under-Alignment: Atomic Preference Enhanced Factuality Tuning for Large Language Models
von: Yuan, Hongbang, et al.
Veröffentlicht: (2024)

Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models
von: Yuan, Hongbang, et al.
Veröffentlicht: (2024)

DTELS: Towards Dynamic Granularity of Timeline Summarization
von: Zhang, Chenlong, et al.
Veröffentlicht: (2024)

Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large Language Models
von: Yuan, Hongbang, et al.
Veröffentlicht: (2024)

RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment
von: Jin, Zhuoran, et al.
Veröffentlicht: (2024)

Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences
von: Jin, Zhuoran, et al.
Veröffentlicht: (2025)

RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
von: Jin, Zhuoran, et al.
Veröffentlicht: (2024)

Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models
von: Jin, Zhuoran, et al.
Veröffentlicht: (2024)

MMR-V: What's Left Unsaid? A Benchmark for Multimodal Deep Reasoning in Videos
von: Zhu, Kejian, et al.
Veröffentlicht: (2025)

MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning
von: Li, Jiachun, et al.
Veröffentlicht: (2026)

One Mind, Many Tongues: A Deep Dive into Language-Agnostic Knowledge Neurons in Large Language Models
von: Cao, Pengfei, et al.
Veröffentlicht: (2024)

CogMG: Collaborative Augmentation Between Large Language Model and Knowledge Graph
von: Zhou, Tong, et al.
Veröffentlicht: (2024)

A Troublemaker with Contagious Jailbreak Makes Chaos in Honest Towns
von: Men, Tianyi, et al.
Veröffentlicht: (2024)

Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models
von: Men, Tianyi, et al.
Veröffentlicht: (2024)

MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language Models
von: Li, Jiachun, et al.
Veröffentlicht: (2024)

Agent-RewardBench: Towards a Unified Benchmark for Reward Modeling across Perception, Planning, and Safety in Real-World Multimodal Agents
von: Men, Tianyi, et al.
Veröffentlicht: (2025)

Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting
von: Chen, Howard, et al.
Veröffentlicht: (2025)

CITI: Enhancing Tool Utilizing Ability in Large Language Models without Sacrificing General Performance
von: Hao, Yupu, et al.
Veröffentlicht: (2024)

Evaluating Personalized Tool-Augmented LLMs from the Perspectives of Personalization and Proactivity
von: Hao, Yupu, et al.
Veröffentlicht: (2025)

Continual Few-shot Event Detection via Hierarchical Augmentation Networks
von: Zhang, Chenlong, et al.
Veröffentlicht: (2024)

MotivGraph-SoIQ: Integrating Motivational Knowledge Graphs and Socratic Dialogue for Enhanced LLM Ideation
von: Lei, Xinping, et al.
Veröffentlicht: (2025)

Mitigating Forgetting Between Supervised and Reinforcement Learning Yields Stronger Reasoners
von: Yuan, Xiangchi, et al.
Veröffentlicht: (2025)

SemEval-2026 Task 12: Abductive Event Reasoning: Towards Real-World Event Causal Inference for Large Language Models
von: Cao, Pengfei, et al.
Veröffentlicht: (2026)

Enhancing Large Language Models with Pseudo- and Multisource- Knowledge Graphs for Open-ended Question Answering
von: Liu, Jiaxiang, et al.
Veröffentlicht: (2024)

Think While Watching: Online Streaming Segment-Level Memory for Multi-Turn Video Reasoning in Multimodal Large Language Models
von: Wang, Lu, et al.
Veröffentlicht: (2026)

Zero-Shot Cross-Lingual Document-Level Event Causality Identification with Heterogeneous Graph Contrastive Transfer Learning
von: He, Zhitao, et al.
Veröffentlicht: (2024)

Focus on Your Question! Interpreting and Mitigating Toxic CoT Problems in Commonsense Reasoning
von: Li, Jiachun, et al.
Veröffentlicht: (2024)

Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models
von: Jin, Zhuoran, et al.
Veröffentlicht: (2024)

MAPLE: Enhancing Review Generation with Multi-Aspect Prompt LEarning in Explainable Recommendation
von: Yang, Ching-Wen, et al.
Veröffentlicht: (2024)

ASP2LJ : An Adversarial Self-Play Laywer Augmented Legal Judgment Framework
von: Chang, Ao, et al.
Veröffentlicht: (2025)

Semantic Pivots Enable Cross-Lingual Transfer in Large Language Models
von: He, Kaiyu, et al.
Veröffentlicht: (2025)

Transparentize the Internal and External Knowledge Utilization in LLMs with Trustworthy Citation
von: Shen, Jiajun, et al.
Veröffentlicht: (2025)

Citekit: A Modular Toolkit for Large Language Model Citation Generation
von: Shen, Jiajun, et al.
Veröffentlicht: (2024)

Fixing the Broken Compass: Diagnosing and Improving Inference-Time Reward Modeling
von: Li, Jiachun, et al.
Veröffentlicht: (2025)

LINKED: Eliciting, Filtering and Integrating Knowledge in Large Language Model for Commonsense Reasoning
von: Li, Jiachun, et al.
Veröffentlicht: (2024)

Pareto Optimal Learning for Estimating Large Language Model Errors
von: Zhao, Theodore, et al.
Veröffentlicht: (2023)

Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference
von: Ji, Jiabao, et al.
Veröffentlicht: (2024)

AgentsCourt: Building Judicial Decision-Making Agents with Court Debate Simulation and Legal Knowledge Augmentation
von: He, Zhitao, et al.
Veröffentlicht: (2024)

Pareto Optimal Code Generation
von: Orlanski, Gabriel, et al.
Veröffentlicht: (2025)

FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the Financial Domain
von: Zhao, Suifeng, et al.
Veröffentlicht: (2025)