Copertina

RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Dang, John, Ahmadian, Arash, Marchisio, Kelly, Kreutzer, Julia, Üstün, Ahmet, Hooker, Sara
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

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

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

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

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

Unlocking Reasoning Capability on Machine Translation in Large Language Models
di: Rajaee, Sara, et al.
Pubblicazione: (2026)

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

Multilingual Arbitrage: Optimizing Data Pools to Accelerate Multilingual Progress
di: Odumakinde, Ayomide, et al.
Pubblicazione: (2024)

Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs
di: Ahmadian, Arash, et al.
Pubblicazione: (2024)

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

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

From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models
di: Pozzobon, Luiza, et al.
Pubblicazione: (2024)

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

Active Preference Optimization for Sample Efficient RLHF
di: Das, Nirjhar, et al.
Pubblicazione: (2024)

WPO: Enhancing RLHF with Weighted Preference Optimization
di: Zhou, Wenxuan, et al.
Pubblicazione: (2024)

When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning
di: Dong, Yijiang River, et al.
Pubblicazione: (2025)

A Systematic Evaluation of Preference Aggregation in Federated RLHF for Pluralistic Alignment of LLMs
di: Srewa, Mahmoud, et al.
Pubblicazione: (2025)

PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference
di: Ji, Jiaming, et al.
Pubblicazione: (2024)

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

Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval
di: Thakur, Nandan, et al.
Pubblicazione: (2023)

Group Preference Optimization: Few-Shot Alignment of Large Language Models
di: Zhao, Siyan, et al.
Pubblicazione: (2023)

When Weak LLMs Speak with Confidence, Preference Alignment Gets Stronger
di: Afzali, Amirabbas, et al.
Pubblicazione: (2026)

Adaptive Margin RLHF via Preference over Preferences
di: Chittepu, Yaswanth, et al.
Pubblicazione: (2025)

CAPO: Confidence Aware Preference Optimization Learning for Multilingual Preferences
di: Pokharel, Rhitabrat, et al.
Pubblicazione: (2025)

Can LLMs Capture Human Preferences?
di: Goli, Ali, et al.
Pubblicazione: (2023)

Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning
di: Singh, Shivalika, et al.
Pubblicazione: (2024)

SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization
di: Sun, Huashan, et al.
Pubblicazione: (2025)

More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness
di: Li, Aaron J., et al.
Pubblicazione: (2024)

Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF
di: Xie, Tengyang, et al.
Pubblicazione: (2024)

From RLHF to Direct Alignment: A Theoretical Unification of Preference Learning for Large Language Models
di: Raheja, Tarun, et al.
Pubblicazione: (2026)

Reward-Robust RLHF in LLMs
di: Yan, Yuzi, et al.
Pubblicazione: (2024)

Whose Morality Do They Speak? Unraveling Cultural Bias in Multilingual Language Models
di: Aksoy, Meltem
Pubblicazione: (2024)

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

On the Limitations of Compute Thresholds as a Governance Strategy
di: Hooker, Sara
Pubblicazione: (2024)

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

Enhancing Multilingual Counterfactual Generation through Alignment-as-Preference Optimization
di: Wang, Yilong, et al.
Pubblicazione: (2026)

POPI: Personalizing LLMs via Optimized Natural Language Preference Inference
di: Chen, Yizhuo, et al.
Pubblicazione: (2025)

Programming by Backprop: An Instruction is Worth 100 Examples When Finetuning LLMs
di: Cook, Jonathan, et al.
Pubblicazione: (2025)

MaxMin-RLHF: Alignment with Diverse Human Preferences
di: Chakraborty, Souradip, et al.
Pubblicazione: (2024)