From the 1 of 26 linked papers with an AI index.
5 papers · 1 filter
Meta-Learning Preferences for Multilingual LLM Alignment
Jiaying Lin, Seongho Son, Nam Phuong Tran +3
The paper introduces a meta-learning method that uses preference data from high-resource languages to quickly adapt large language models to low-resource languages with very few hu…
Overton Pluralistic Reinforcement Learning for Large Language Models
Yu Fu, Seongho Son, Ilija Bogunovic
Existing alignment paradigms remain limited in capturing the pluralistic nature of human values. Overton Pluralism addresses this gap by generating responses with diverse perspecti…
Multi-Task GRPO: Reliable LLM Reasoning Across Tasks
Shyam Sundhar Ramesh, Xiaotong Ji, Matthieu Zimmer +5
RL-based post-training with GRPO is widely used to improve large language models on individual reasoning tasks. However, real-world deployment requires reliable performance across…
This Is Your Doge, If It Please You: Exploring Deception and Robustness in Mixture of LLMs
Lorenz Wolf, Sangwoong Yoon, Ilija Bogunovic
Mixture of large language model (LLMs) Agents (MoA) architectures achieve state-of-the-art performance on prominent benchmarks like AlpacaEval 2.0 by leveraging the collaboration o…
Group Robust Preference Optimization in Reward-free RLHF
Shyam Sundhar Ramesh, Yifan Hu, Iason Chaimalas +4
Adapting large language models (LLMs) for specific tasks usually involves fine-tuning through reinforcement learning with human feedback (RLHF) on preference data. While these data…