5 papers
Camellia: Benchmarking Cultural Biases in LLMs for Asian Languages
Tarek Naous, Anagha Savit, Carlos Rafael Catalan +17
As Large Language Models (LLMs) develop stronger multilingual capabilities, their sensitivity to culturally diverse entities becomes increasingly important. Prior work by Naous et…
Learning to Route Languages for Multilingual Policy Optimization
Geyang Guo, Hiromi Wakaki, Yuki Mitsufuji +2
Large language models~(LLMs) are trained on heterogeneous multilingual corpora, yet existing policy optimization methods often implicitly restrict each training question to a singl…
CARE: Multilingual Human Preference Learning for Cultural Awareness
Geyang Guo, Tarek Naous, Hiromi Wakaki +4
Language Models (LMs) are typically tuned with human preferences to produce helpful responses, but the impact of preference tuning on the ability to handle culturally diverse queri…
Preference Optimization for Reasoning with Pseudo Feedback
Fangkai Jiao, Geyang Guo, Xingxing Zhang +3
Preference optimization techniques, such as Direct Preference Optimization (DPO), are frequently employed to enhance the reasoning capabilities of large language models (LLMs) in d…
SFT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity
Xinyu Yang, Jixuan Leng, Geyang Guo +5
Current PEFT methods for LLMs can achieve either high quality, efficient training, or scalable serving, but not all three simultaneously. To address this limitation, we investigate…