liveBook · Manning

Discovery

As explained in Introduction to Generative AI, Second Edition

Discovery is the formal legal process in which parties to a lawsuit exchange information about witnesses and evidence to be presented at trial.

Discovery is the formal legal process in which opposing parties exchange information about the witnesses and evidence they expect to present at trial. Lawsuits may generate thousands of documents and make discovery last months or years. section 6.3

E-discovery software has long helped index these documents and locate relevant information, usually through searches for specific terms. Large language models (LLMs) could extend this workflow by summarizing documents and identifying materials that support a particular legal argument. section 6.3

Discovery-related work can include:

  • Exchanging witness and evidence information between lawsuit parties. section 6.3
  • Indexing large document collections and searching them for relevant terms. section 6.3
  • Generating brief document summaries or locating evidence connected to a specific argument. section 6.3

How Introduction to Generative AI, Second Edition covers it

How deep it goes
Defines discovery and sketches document-search and LLM-assisted analysis without detailing legal procedures or implementation.
Examples
Uses thousands of exchanged documents, term searches, document summaries, and evidence supporting a legal argument as examples.
What you can do after
Evaluate potential uses of e-discovery software and LLMs for organizing documents and finding litigation-relevant evidence.
How it connects
Connects discovery with e-discovery, legal research, document embeddings, similarity, and large language models.

Also explained in

Compare how 4 books explain discovery →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Introduction to Generative AI, Second Edition. The section links point to the parts of the book it draws on.