Image de couverture de livre

RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chaudhari, Shreyas, Aggarwal, Pranjal, Murahari, Vishvak, Rajpurohit, Tanmay, Kalyan, Ashwin, Narasimhan, Karthik, Deshpande, Ameet, da Silva, Bruno Castro
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

GEO: Generative Engine Optimization
par: Aggarwal, Pranjal, et autres
Publié: (2023)

Probing AI Safety with Source Code
par: Narayan, Ujwal, et autres
Publié: (2025)

Agent Context Protocols Enhance Collective Inference
par: Bhardwaj, Devansh, et autres
Publié: (2025)

PersonaGym: Evaluating Persona Agents and LLMs
par: Samuel, Vinay, et autres
Publié: (2024)

QualEval: Qualitative Evaluation for Model Improvement
par: Murahari, Vishvak, et autres
Publié: (2023)

Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy Evaluation
par: Chaudhari, Shreyas, et autres
Publié: (2024)

Language Models can Subtly Deceive Without Lying: A Case Study on Strategic Phrasing in Legislation
par: Dogra, Atharvan, et autres
Publié: (2024)

Which Rewards Matter? Reward Selection for Reinforcement Learning under Limited Feedback
par: Chaudhari, Shreyas, et autres
Publié: (2025)

Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs
par: Gupta, Shashank, et autres
Publié: (2023)

Engagement Undermines Safety: How Stereotypes and Toxicity Shape Humor in Language Models
par: Dogra, Atharvan, et autres
Publié: (2025)

LLMs are Superior Feedback Providers: Bootstrapping Reasoning for Lie Detection with Self-Generated Feedback
par: Banerjee, Tanushree, et autres
Publié: (2024)

L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
par: Aggarwal, Pranjal, et autres
Publié: (2025)

Dimension-Free Parameterized Approximation Schemes for Hybrid Clustering
par: Gadekar, Ameet, et autres
Publié: (2025)

RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
par: Lee, Harrison, et autres
Publié: (2023)

MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions
par: Chai, Yekun, et autres
Publié: (2024)

Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback
par: Ji, Jiaming, et autres
Publié: (2025)

Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback
par: Yuan, Yifu, et autres
Publié: (2024)

Clustering under Constraints: Efficient Parameterized Approximation Schemes
par: Bhore, Sujoy, et autres
Publié: (2025)

Programming with Pixels: Can Computer-Use Agents do Software Engineering?
par: Aggarwal, Pranjal, et autres
Publié: (2025)

Enhancing LLMs for Physics Problem-Solving using Reinforcement Learning with Human-AI Feedback
par: Anand, Avinash, et autres
Publié: (2024)

Vanishing sheaves and the geometric Whittaker model
par: Roman Bezrukavnikov, et autres
Publié: (2025)

Character Sheaves on Tori over Local Fields
par: Deshpande, Tanmay, et autres
Publié: (2023)

Vanishing sheaves and the geometric Whittaker model
par: Bezrukavnikov, Roman, et autres
Publié: (2023)

Minimum Envy Graphical House Allocation Beyond Identical Valuations
par: Inamdar, Tanmay, et autres
Publié: (2026)

ACE-RLHF: Automated Code Evaluation and Socratic Feedback Generation Tool using Large Language Models and Reinforcement Learning with Human Feedback
par: Rahman, Tasnia, et autres
Publié: (2025)

SAFE: Stable Alignment Finetuning with Entropy-Aware Predictive Control for Reinforcement Learning from Human Feedback (RLHF)
par: Maity, Dipan
Publié: (2026)

Deciphering the origins and growth of supermassive black holes
par: Aggarwal, Yash
Publié: (2021)

RLHF Fine-Tuning of LLMs for Alignment with Implicit User Feedback in Conversational Recommenders
par: Yang, Zhongheng, et autres
Publié: (2025)

A Construction of the Symmetric Monoidal Structure of the Geometric Whittaker Model
par: Choudhury, Ashutosh Roy, et autres
Publié: (2024)

ChatGLM-RLHF: Practices of Aligning Large Language Models with Human Feedback
par: Hou, Zhenyu, et autres
Publié: (2024)

A Survey of Reinforcement Learning For Economics
par: Rawat, Pranjal
Publié: (2026)

Approximating Auction Equilibria with Reinforcement Learning
par: Rawat, Pranjal
Publié: (2024)

When Benchmarks Talk: Re-Evaluating Code LLMs with Interactive Feedback
par: Pan, Jane, et autres
Publié: (2025)

A Critical Study of What Code-LLMs (Do Not) Learn
par: Anand, Abhinav, et autres
Publié: (2024)

On The Global Convergence Of Online RLHF With Neural Parametrization
par: Gaur, Mudit, et autres
Publié: (2024)

ReLU Networks as Random Functions: Their Distribution in Probability Space
par: Chaudhari, Shreyas, et autres
Publié: (2025)

AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement
par: Aggarwal, Pranjal, et autres
Publié: (2024)

Gym-Anything: Turn any Software into an Agent Environment
par: Aggarwal, Pranjal, et autres
Publié: (2026)

Reward-Robust RLHF in LLMs
par: Yan, Yuzi, et autres
Publié: (2024)

Evaluating Defences against Unsafe Feedback in RLHF
par: Rosati, Domenic, et autres
Publié: (2024)