Redefining Proactivity for Information Seeking Dialogue
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929594680999936 |
|---|---|
| author | Lee, Jing Yang Kim, Seokhwan Mehta, Kartik Kao, Jiun-Yu Lin, Yu-Hsiang Gupta, Arpit |
| author_facet | Lee, Jing Yang Kim, Seokhwan Mehta, Kartik Kao, Jiun-Yu Lin, Yu-Hsiang Gupta, Arpit |
| contents | Information-Seeking Dialogue (ISD) agents aim to provide accurate responses to user queries. While proficient in directly addressing user queries, these agents, as well as LLMs in general, predominantly exhibit reactive behavior, lacking the ability to generate proactive responses that actively engage users in sustained conversations. However, existing definitions of proactive dialogue in this context do not focus on how each response actively engages the user and sustains the conversation. Hence, we present a new definition of proactivity that focuses on enhancing the `proactiveness' of each generated response via the introduction of new information related to the initial query. To this end, we construct a proactive dialogue dataset comprising 2,000 single-turn conversations, and introduce several automatic metrics to evaluate response `proactiveness' which achieved high correlation with human annotation. Additionally, we introduce two innovative Chain-of-Thought (CoT) prompts, the 3-step CoT and the 3-in-1 CoT prompts, which consistently outperform standard prompts by up to 90% in the zero-shot setting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_15297 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Redefining Proactivity for Information Seeking Dialogue Lee, Jing Yang Kim, Seokhwan Mehta, Kartik Kao, Jiun-Yu Lin, Yu-Hsiang Gupta, Arpit Computation and Language Artificial Intelligence Information-Seeking Dialogue (ISD) agents aim to provide accurate responses to user queries. While proficient in directly addressing user queries, these agents, as well as LLMs in general, predominantly exhibit reactive behavior, lacking the ability to generate proactive responses that actively engage users in sustained conversations. However, existing definitions of proactive dialogue in this context do not focus on how each response actively engages the user and sustains the conversation. Hence, we present a new definition of proactivity that focuses on enhancing the `proactiveness' of each generated response via the introduction of new information related to the initial query. To this end, we construct a proactive dialogue dataset comprising 2,000 single-turn conversations, and introduce several automatic metrics to evaluate response `proactiveness' which achieved high correlation with human annotation. Additionally, we introduce two innovative Chain-of-Thought (CoT) prompts, the 3-step CoT and the 3-in-1 CoT prompts, which consistently outperform standard prompts by up to 90% in the zero-shot setting. |
| title | Redefining Proactivity for Information Seeking Dialogue |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2410.15297 |