5 papers
Cheaper, Better, Faster, Stronger: Robust Text-to-SQL without Chain-of-Thought or Fine-Tuning
Yusuf Denizay Dönder, Derek Hommel, Andrea W Wen-Yi +2
LLMs are effective at code generation tasks like text-to-SQL, but is it worth the cost? Many state-of-the-art approaches use non-task-specific LLM techniques including Chain-of-Tho…
Do Chinese models speak Chinese languages?
Andrea W Wen-Yi, Unso Eun Seo Jo, David Mimno
The release of top-performing open-weight LLMs has cemented China's role as a leading force in AI development. Do these models support languages spoken in China? Or do they support…
Automate or Assist? The Role of Computational Models in Identifying Gendered Discourse in US Capital Trial Transcripts
Andrea W Wen-Yi, Kathryn Adamson, Nathalie Greenfield +4
The language used by US courtroom actors in criminal trials has long been studied for biases. However, systematic studies for bias in high-stakes court trials have been difficult,…
How Chinese are Chinese Language Models? The Puzzling Lack of Language Policy in China's LLMs
Andrea W Wen-Yi, Unso Eun Seo Jo, Lu Jia Lin +1
Contemporary language models are increasingly multilingual, but Chinese LLM developers must navigate complex political and business considerations of language diversity. Language p…
Hyperpolyglot LLMs: Cross-Lingual Interpretability in Token Embeddings
Andrea W Wen-Yi, David Mimno
Cross-lingual transfer learning is an important property of multilingual large language models (LLMs). But how do LLMs represent relationships between languages? Every language mod…