Imagen de Portada

Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ahmadian, Arash, Cremer, Chris, Gallé, Matthias, Fadaee, Marzieh, Kreutzer, Julia, Pietquin, Olivier, Üstün, Ahmet, Hooker, Sara
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning I.2.7
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs
por: Dang, John, et al.
Publicado: (2024)

The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm
por: Aakanksha, et al.
Publicado: (2024)

SimMerge: Learning to Select Merge Operators from Similarity Signals
por: Bolton, Oliver, et al.
Publicado: (2026)

LLM See, LLM Do: Guiding Data Generation to Target Non-Differentiable Objectives
por: Shimabucoro, Luísa, et al.
Publicado: (2024)

Mix Data or Merge Models? Optimizing for Diverse Multi-Task Learning
por: Aakanksha, et al.
Publicado: (2024)

Verification Limits Code LLM Training
por: Gureja, Srishti, et al.
Publicado: (2025)

Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers
por: D'souza, Daniel, et al.
Publicado: (2025)

The Art of Asking: Multilingual Prompt Optimization for Synthetic Data
por: Mora, David, et al.
Publicado: (2025)

A Post-trainer's Guide to Multilingual Training Data: Uncovering Cross-lingual Transfer Dynamics
por: Shimabucoro, Luisa, et al.
Publicado: (2025)

Diversify and Conquer: Diversity-Centric Data Selection with Iterative Refinement
por: Yu, Simon, et al.
Publicado: (2024)

The Multilingual Divide and Its Impact on Global AI Safety
por: Peppin, Aidan, et al.
Publicado: (2025)

Agents Explore but Agents Ignore: LLMs Lack Environmental Curiosity
por: Engländer, Leon, et al.
Publicado: (2026)

To Code, or Not To Code? Exploring Impact of Code in Pre-training
por: Aryabumi, Viraat, et al.
Publicado: (2024)

Making, not Taking, the Best of N
por: Khairi, Ammar, et al.
Publicado: (2025)

How Well Do LLMs Imitate Human Writing Style?
por: Jemama, Rebira, et al.
Publicado: (2025)

Fine-Tuning LLMs with Fine-Grained Human Feedback on Text Spans
por: CH-Wang, Sky, et al.
Publicado: (2025)

Déjà Vu: Multilingual LLM Evaluation through the Lens of Machine Translation Evaluation
por: Kreutzer, Julia, et al.
Publicado: (2025)

If You Can't Use Them, Recycle Them: Optimizing Merging at Scale Mitigates Performance Tradeoffs
por: Khalifa, Muhammad, et al.
Publicado: (2024)

Human-Aligned Enhancement of Programming Answers with LLMs Guided by User Feedback
por: Bappon, Suborno Deb, et al.
Publicado: (2026)

Automatic WordNet Construction Using Markov Chain Monte Carlo
por: Marzieh Fadaee
Publicado: (2013)

One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizers
por: Abagyan, Diana, et al.
Publicado: (2025)

Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion
por: Flet-Berliac, Yannis, et al.
Publicado: (2024)

The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It
por: Yong, Zheng-Xin, et al.
Publicado: (2025)

Please Make it Sound like Human: Encoder-Decoder vs. Decoder-Only Transformers for AI-to-Human Text Style Transfer
por: Paneru, Utsav
Publicado: (2026)

How Does Quantization Affect Multilingual LLMs?
por: Marchisio, Kelly, et al.
Publicado: (2024)

A Framework for Fine-Tuning LLMs using Heterogeneous Feedback
por: Aponte, Ryan, et al.
Publicado: (2024)

The Disparate Impacts of Speculative Decoding
por: Sandler, Jameson, et al.
Publicado: (2025)

Nexus: Specialization meets Adaptability for Efficiently Training Mixture of Experts
por: Gritsch, Nikolas, et al.
Publicado: (2024)

When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs
por: Khairi, Ammar, et al.
Publicado: (2025)

LLMs and the Human Condition
por: Wallis, Peter
Publicado: (2024)

Reinforcement Learning for Latent-Space Thinking in LLMs
por: Özeren, Enes, et al.
Publicado: (2025)

Self-Improving Robust Preference Optimization
por: Choi, Eugene, et al.
Publicado: (2024)

MASH: Evading Black-Box AI-Generated Text Detectors via Style Humanization
por: Gu, Yongtong, et al.
Publicado: (2026)

Averaging log-likelihoods in direct alignment
por: Grinsztajn, Nathan, et al.
Publicado: (2024)

Aya Vision: Advancing the Frontier of Multilingual Multimodality
por: Dash, Saurabh, et al.
Publicado: (2025)

Do Language Models Mirror Human Confidence? Exploring Psychological Insights to Address Overconfidence in LLMs
por: Xu, Chenjun, et al.
Publicado: (2025)

Toward Beginner-Friendly LLMs for Language Learning: Controlling Difficulty in Conversation
por: Jin, Meiqing, et al.
Publicado: (2025)

Revisiting Word Embeddings in the LLM Era
por: Mahajan, Yash, et al.
Publicado: (2024)

Diatom assemblage in surface sediments of the Laptev Sea
por: Cremer, Holger, et al.
Publicado: (1998)

Personality, Role, and Expressive Style in Large Language Models: An Interactionist Analysis
por: Nagao, Moe, et al.
Publicado: (2026)