Image de couverture de livre

Don't Forget Your Reward Values: Language Model Alignment via Value-based Calibration

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Mao, Xin, Li, Feng-Lin, Xu, Huimin, Zhang, Wei, Luu, Anh Tuan
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models
par: Chen, Yanjun, et autres
Publié: (2024)

Don't Forget to Connect! Improving RAG with Graph-based Reranking
par: Dong, Jialin, et autres
Publié: (2024)

As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss
par: Mao, Xin, et autres
Publié: (2024)

HAVE: Head-Adaptive Gating and ValuE Calibration for Hallucination Mitigation in Large Language Models
par: Tong, Xin, et autres
Publié: (2025)

sDPO: Don't Use Your Data All at Once
par: Kim, Dahyun, et autres
Publié: (2024)

Language Models Don't Learn the Physical Manifestation of Language
par: Lee, Bruce W., et autres
Publié: (2024)

Don't Think Twice! Over-Reasoning Impairs Confidence Calibration
par: Lacombe, Romain, et autres
Publié: (2025)

Towards Reliable Truth-Aligned Uncertainty Estimation in Large Language Models
par: Srey, Ponhvoan, et autres
Publié: (2026)

Learning Uncertainty from Sequential Internal Dispersion in Large Language Models
par: Srey, Ponhvoan, et autres
Publié: (2026)

Inference-Time Language Model Alignment via Integrated Value Guidance
par: Liu, Zhixuan, et autres
Publié: (2024)

Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models
par: Zhao, Shuai, et autres
Publié: (2023)

Benchmarking Multi-National Value Alignment for Large Language Models
par: Shi, Weijie, et autres
Publié: (2025)

Internal Value Alignment in Large Language Models through Controlled Value Vector Activation
par: Jin, Haoran, et autres
Publié: (2025)

VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language Models
par: Kim, Woojin, et autres
Publié: (2026)

Diverse Human Value Alignment for Large Language Models via Ethical Reasoning
par: Wang, Jiahao, et autres
Publié: (2025)

SCOPE: Compress Mathematical Reasoning Steps for Efficient Automated Process Annotation
par: Xu, Huimin, et autres
Publié: (2025)

Unsupervised Hallucination Detection by Inspecting Reasoning Processes
par: Srey, Ponhvoan, et autres
Publié: (2025)

A Survey on Neural Topic Models: Methods, Applications, and Challenges
par: Wu, Xiaobao, et autres
Publié: (2024)

Don't Pay Attention
par: Hammoud, Mohammad, et autres
Publié: (2025)

Process Reward Model with Q-Value Rankings
par: Li, Wendi, et autres
Publié: (2024)

Don't Forget the Critic: Value-Based Data Rehearsal for Multi-Cyclic Continual Reinforcement Learning
par: Poole, Benjamin, et autres
Publié: (2026)

Do Retrieval Augmented Language Models Know When They Don't Know?
par: Zhou, Youchao, et autres
Publié: (2025)

Don't Let It Fade: Preserving Edits in Diffusion Language Models via Token Timestep Allocation
par: Kim, Woojin, et autres
Publié: (2025)

Reasoning Models Reason Well, Until They Don't
par: Rameshkumar, Revanth, et autres
Publié: (2025)

Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning
par: Xu, Huimin, et autres
Publié: (2025)

Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning
par: Zhao, Shuai, et autres
Publié: (2024)

Who's Who: Large Language Models Meet Knowledge Conflicts in Practice
par: Pham, Quang Hieu, et autres
Publié: (2024)

Don't Change My View: Ideological Bias Auditing in Large Language Models
par: Kröger, Paul, et autres
Publié: (2025)

Value Augmented Sampling for Language Model Alignment and Personalization
par: Han, Seungwook, et autres
Publié: (2024)

Towards the TopMost: A Topic Modeling System Toolkit
par: Wu, Xiaobao, et autres
Publié: (2023)

s3: You Don't Need That Much Data to Train a Search Agent via RL
par: Jiang, Pengcheng, et autres
Publié: (2025)

F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare
par: Plyusov, Daniil, et autres
Publié: (2026)

VAL-Bench: Belief Consistency as a measure for Value Alignment in Language Models
par: Gupta, Aman, et autres
Publié: (2025)

Honest AI: Fine-Tuning "Small" Language Models to Say "I Don't Know", and Reducing Hallucination in RAG
par: Chen, Xinxi, et autres
Publié: (2024)

Modeling Dynamic Topics in Chain-Free Fashion by Evolution-Tracking Contrastive Learning and Unassociated Word Exclusion
par: Wu, Xiaobao, et autres
Publié: (2024)

Gradual Vigilance and Interval Communication: Enhancing Value Alignment in Multi-Agent Debates
par: Zou, Rui, et autres
Publié: (2024)

Flames: Benchmarking Value Alignment of LLMs in Chinese
par: Huang, Kexin, et autres
Publié: (2023)

ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation
par: Zheng, Jingnan, et autres
Publié: (2024)

Large Language Models Must Be Taught to Know What They Don't Know
par: Kapoor, Sanyam, et autres
Publié: (2024)

Know What You Don't Know: Uncertainty Calibration of Process Reward Models
par: Park, Young-Jin, et autres
Publié: (2025)