[3G5-GS-6] Language media processing:

[3G5-GS-6-01] Training of Retrievers for Buzzer Quizzes using Questions with a Length Limitation

〇Toumi Sasaki¹, Shunsuke Kobayashi¹, Daisuke Kawahara^1,2 (1. Waseda University, 2. National Institute of Informatics, LLMC)

Keywords:LLM, Question Answering, Quiz

In buzzer quizzes, retriever-reader models are commonly used, where a retriever extracts relevant information and a reader derives the answer. However, traditional retriever training uses full questions, while buzzer quiz players only hear partial questions, causing a mismatch. To address this problem, we limit question length during training and apply curriculum learning. This approach successfully creates a model that performs well at various points in the question. Additionally, our analysis reveals that the retriever’s performance varies based on question format and training length compatibility.