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

Abstract Legal professionals need to write analyses that rely on citations to relevant precedents, i.e., previous case decisions. Intelligent systems assisting legal professionals in writing such documents provide great benefits but are challenging to design.[…]

Read More

Abstract Current Natural Language Processing systems rely heavily on Large Language Models (LLMs) which are trained rather naively on large amounts of text using autoregressive next token prediction. Often, they are fine-tuned to mimic human[…]

Read More

Abstract While large language models (LLMs) have revolutionized AI, their token-level processing contrasts sharply with human cognition’s multi-level abstraction. This talk explores moving beyond token-based manipulation to reason in a latent space. We introduce the[…]

Read More

Abstract This is a casual discussion with Oren Etzioni and will touch upon various topics, including the advancement of AI, its effects on society and politics and entrepreneurship in  today’s technological era. There will also be[…]

Read More