Interpreting Answers to Yes-No Questions in Dialogues from Multiple Domains

arXiv:2404.16262v1 Announce Type: new
Abstract: People often answer yes-no questions without explicitly saying yes, no, or similar polar keywords. Figuring out the meaning of indirect answers is challenging, even for large language models. In this paper, we investigate this problem working with dialogues from multiple domains. We present new benchmarks in three diverse domains: movie scripts, tennis interviews, and airline customer service. We present an approach grounded on distant supervision and blended training to quickly adapt to a new dialogue …

abstract arxiv benchmarks cs.cl domains keywords language language models large language large language models meaning multiple paper people polar questions type