Evaluating LLMs on Document-Based QA: Exact Answer Selection and Numerical Extraction using Cogtale dataset

no code implementations • 14 Nov 2023 • Zafaryab Rasool, Stefanus Kurniawan, Sherwin Balugo, Scott Barnett, Rajesh Vasa, Courtney Chesser, Benjamin M. Hampstead, Sylvie Belleville, Kon Mouzakis, Alex Bahar-Fuchs

In this paper, we specifically focus on this underexplored context and conduct empirical analysis of LLMs (GPT-4 and GPT-3. 5) on question types, including single-choice, yes-no, multiple-choice, and number extraction questions from documents in zero-shot setting.

Answer Selection Information Retrieval +2