From the 1 of 6 linked papers with an AI index.
6 papers
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…
SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks
Seongho Son, Sangwoong Yoon, Jiahua Tang +3
Large language models (LLMs) embedded in multi-turn agentic harnesses are reshaping software engineering (SWE), but routing every task to a frontier model is wasteful when many iss…
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…
Robust Multi-Objective Controlled Decoding of Large Language Models
Seongho Son, William Bankes, Sangwoong Yoon +3
We introduce Robust Multi-Objective Decoding (RMOD), a novel inference-time algorithm that robustly aligns Large Language Models (LLMs) to multiple human objectives (e.g., instruct…
Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift
Seongho Son, William Bankes, Sayak Ray Chowdhury +2
Current Large Language Model (LLM) preference optimization algorithms do not account for temporal preference drift, which can lead to severe misalignment. To address this limitatio…
RSPO: Regularized Self-Play Alignment of Large Language Models
Xiaohang Tang, Sangwoong Yoon, Seongho Son +3
Self-play alignment has emerged as an effective approach for fine-tuning large language models (LLMs), formulating preference optimization as a two-player game. However, the regula…