Abstract While state-of-the-art models for machine translation and natural language understanding perform well on high-resource members of (some of) the world’s language families, they degrade on closely-related languages, dialects, and variants of these languages, which[…]

Read More

Abstract Pretrained language models have brought revolutionary progress to information-seeking in the English world. While the advance is exciting, how to transfer such progress into non-English, especially lower resource languages, presents new challenges that require[…]

Read More

Abstract The paradigm of training large-scale foundation models has driven significant advancements in multimodal AI. However, pursuing further performance gains solely through model scaling is becoming impractical due to rising computational costs and resource limitations.[…]

Read More

Abstract Information is one of the most powerful forces in today’s digital era, shaping decisions at every level of society. While the ways we seek and access information have evolved over time, core challenges—such as[…]

Read More

Abstract Language models (LMs) are highly effective at understanding and generating text, holding immense potential as intuitive, personalized interfaces for accessing information. Expanding their ability to gather and synthesize large volumes of information will further[…]

Read More

Abstract This presentation will cover two papers, both on LLMs’ abilities to handle complex legal tasks.  First is the Shelter Check dataset, a curated set of past tax-minimization schemes.  We test o1 and claude-3.5’s abilities[…]

Read More

Abstract In this talk, Igor will share the latest findings from his research group on the development, evaluation, and deployment of large language models (LLMs) and their multi-modal extensions. We will outline the end-to-end pipeline,[…]

Read More