In the common law system, the process of searching for relevant information for a legal case is known as "discovery." Legal practitioners once had to manually sift through physical paper documents to identify relevant information for their cases before the transition to electronic storage. Today, given the vast amount of electronically stored information (ESI) that may be subject to discovery, these processes increasingly depend on collaborative efforts between information retrieval, machine learning models, and human legal practitioners. In this talk, I will delve into the design of efficient and effective search processes for legal electronic discovery. Moreover, I will explore how the lessons we have learned from these processes can offer insights for the development of the next generation of LLM-powered systems.
Eugene Yang is a visiting research scientist at the Human Language Technology Center of Excellence (HLTCOE) at Johns Hopkins University. Eugene received his Ph.D. from Georgetown University, where he worked on High Recall retrieval for electronic discovery, under the guidance of Ophir Frieder and David D. Lewis. His work has influence the design of retrieval systems used by law firms and legal service providers in the United States. He previously consulted for Relativity, a leading software company for electronic discovery. He currently works with Redgrave Data on neural retrieval systems and the adaptation of LLM in professional search environments.