Year: 2024
Type: preprint
Abstract: Large language models like GPT have proven widely successful on natural language understanding tasks based on written text documents. In this paper, we investigate an LLM's performance on recordings of a group oral communication task in which utterances are often truncated or not well-formed. We propose a new group task experiment involving a puzzle with several milestones that can be achieved in any order. We investigate methods for processing transcripts to detect if, when, and by whom a milestone has been completed. We demonstrate that iteratively prompting GPT with transcription chunks outperforms semantic similarity search methods using text embeddings, and further discuss the quality and randomness of GPT responses under different context window sizes.
Source: arXiv (Cornell University)
Authors: Duan, Zhuoxu, Yang, Zhengye, Westby, Samuel, Riedl, Christoph, Welles, Brooke Foucault, Radke, Richard J.
Institutions: Rensselaer Polytechnic Institute, Northeastern University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4399794597