5 papers
FactNet: A Billion-Scale Knowledge Graph for Multilingual Factual Grounding
Yingli Shen, Wen Lai, Jie Zhou +7
Large language models hallucinate factual claims and struggle to ground their outputs in retrievable evidence, particularly in non-English languages. Existing resources impose a tr…
DiffScore: Text Evaluation Beyond Autoregressive Likelihood
Wen Lai, Yingli Shen, Dingnan Jin +4
Autoregressive language models are widely used for text evaluation, however, their left-to-right factorization introduces positional bias, i.e., early tokens are scored with only l…
DCAD-2000: A Multilingual Dataset across 2000+ Languages with Data Cleaning as Anomaly Detection
Yingli Shen, Wen Lai, Shuo Wang +4
The rapid development of multilingual large language models (LLMs) highlights the need for high-quality, diverse, and well-curated multilingual datasets. In this paper, we introduc…
From Unaligned to Aligned: Scaling Multilingual LLMs with Multi-Way Parallel Corpora
Yingli Shen, Wen Lai, Shuo Wang +4
Continued pretraining and instruction tuning on large-scale multilingual data have proven to be effective in scaling large language models (LLMs) to low-resource languages. However…
Joint Localization and Activation Editing for Low-Resource Fine-Tuning
Wen Lai, Alexander Fraser, Ivan Titov
Parameter-efficient fine-tuning (PEFT) methods, such as LoRA, are commonly used to adapt LLMs. However, the effectiveness of standard PEFT methods is limited in low-resource scenar…