9 papers
The "Knowledge-Behavior Gap" in Cultural Taboo Safety of Large Language Models
Ying He, Sihang Jiang, Xingzhou Chen +6
Cultural taboo safety is essential for deploying large language models (LLMs), as culturally insensitive outputs may cause offense or even social harm. However, existing cultural b…
M-DaQ: Retrieving Samples with Multilingual Diversity and Quality for Instruction Fine-Tuning Datasets
Chunguang Zhao, Yilun Liu, Pufan Zeng +10
Multilingual instruction fine-tuning (IFT) empowers large language models to generalize across diverse linguistic and cultural contexts; however, high-quality, systematically curat…
The GaoYao Benchmark: A Comprehensive Framework for Evaluating Multilingual and Multicultural Abilities of Large Language Models
Yilun Liu, Chunguang Zhao, Mengyao Piao +14
Evaluating the multilingual and multicultural capabilities of Large Language Models (LLMs) is essential for their global utility. However, current benchmarks face three critical li…
C-Mining: Unsupervised Discovery of Seeds for Cultural Data Synthesis via Geometric Misalignment
Pufan Zeng, Yilun Liu, Mingchen Dai +12
Achieving cultural alignment in Large Language Models (LLMs) increasingly depends on synthetic data generation. For such synthesis, the most vital initial step is seed curation; ho…
ELSPR: Evaluator LLM Training Data Self-Purification on Non-Transitive Preferences via Tournament Graph Reconstruction
Yan Yu, Yilun Liu, Minggui He +9
Pairwise evaluation of large language models (LLMs) has become the dominant paradigm for benchmarking open-ended tasks, yet non-transitive preferences, where evaluators prefer A ov…
MIDB: Multilingual Instruction Data Booster for Enhancing Cultural Equality in Multilingual Instruction Synthesis
Yilun Liu, Chunguang Zhao, Xinhua Yang +9
Despite doubts on data quality, instruction synthesis has been widely applied into instruction tuning (IT) of LLMs as an economic and rapid alternative. Recent endeavors focus on i…