4 papers
Language Unalignability: Why Some Concepts Resist Cross-Cultural Benchmark Evaluation
Shu-Kai Hsieh, Da-Chen Lian
Current evaluation of multilingual Large Language Models (LLMs) rests on an implicit Translation-Isomorphism Assumption (TIA): that semantic structures across languages are congrue…
LingBench++: A Linguistically-Informed Benchmark and Reasoning Framework for Multi-Step and Cross-Cultural Inference with LLMs
Da-Chen Lian, Ri-Sheng Huang, Pin-Er Chen +7
We propose LingBench++, a linguistically-informed benchmark and reasoning framework designed to evaluate large language models (LLMs) on complex linguistic tasks inspired by the In…
Continual Pre-Training is (not) What You Need in Domain Adaption
Pin-Er Chen, Da-Chen Lian, Shu-Kai Hsieh +8
The recent advances in Legal Large Language Models (LLMs) have transformed the landscape of legal research and practice by automating tasks, enhancing research precision, and suppo…
A Topic-aware Comparable Corpus of Chinese Variations
Da-Chen Lian, Shu-Kai Hsieh
This study aims to fill the gap by constructing a topic-aware comparable corpus of Mainland Chinese Mandarin and Taiwanese Mandarin from the social media in Mainland China and Taiw…