Empowering Language Models with Active Inquiry for Deeper Understanding
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913224632303616 |
|---|---|
| author | Pang, Jing-Cheng Fan, Heng-Bo Wang, Pengyuan Xiao, Jia-Hao Tang, Nan Yang, Si-Hang Jia, Chengxing Huang, Sheng-Jun Yu, Yang |
| author_facet | Pang, Jing-Cheng Fan, Heng-Bo Wang, Pengyuan Xiao, Jia-Hao Tang, Nan Yang, Si-Hang Jia, Chengxing Huang, Sheng-Jun Yu, Yang |
| contents | The rise of large language models (LLMs) has revolutionized the way that we interact with artificial intelligence systems through natural language. However, LLMs often misinterpret user queries because of their uncertain intention, leading to less helpful responses. In natural human interactions, clarification is sought through targeted questioning to uncover obscure information. Thus, in this paper, we introduce LaMAI (Language Model with Active Inquiry), designed to endow LLMs with this same level of interactive engagement. LaMAI leverages active learning techniques to raise the most informative questions, fostering a dynamic bidirectional dialogue. This approach not only narrows the contextual gap but also refines the output of the LLMs, aligning it more closely with user expectations. Our empirical studies, across a variety of complex datasets where LLMs have limited conversational context, demonstrate the effectiveness of LaMAI. The method improves answer accuracy from 31.9% to 50.9%, outperforming other leading question-answering frameworks. Moreover, in scenarios involving human participants, LaMAI consistently generates responses that are superior or comparable to baseline methods in more than 82% of the cases. The applicability of LaMAI is further evidenced by its successful integration with various LLMs, highlighting its potential for the future of interactive language models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_03719 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Empowering Language Models with Active Inquiry for Deeper Understanding Pang, Jing-Cheng Fan, Heng-Bo Wang, Pengyuan Xiao, Jia-Hao Tang, Nan Yang, Si-Hang Jia, Chengxing Huang, Sheng-Jun Yu, Yang Computation and Language Artificial Intelligence The rise of large language models (LLMs) has revolutionized the way that we interact with artificial intelligence systems through natural language. However, LLMs often misinterpret user queries because of their uncertain intention, leading to less helpful responses. In natural human interactions, clarification is sought through targeted questioning to uncover obscure information. Thus, in this paper, we introduce LaMAI (Language Model with Active Inquiry), designed to endow LLMs with this same level of interactive engagement. LaMAI leverages active learning techniques to raise the most informative questions, fostering a dynamic bidirectional dialogue. This approach not only narrows the contextual gap but also refines the output of the LLMs, aligning it more closely with user expectations. Our empirical studies, across a variety of complex datasets where LLMs have limited conversational context, demonstrate the effectiveness of LaMAI. The method improves answer accuracy from 31.9% to 50.9%, outperforming other leading question-answering frameworks. Moreover, in scenarios involving human participants, LaMAI consistently generates responses that are superior or comparable to baseline methods in more than 82% of the cases. The applicability of LaMAI is further evidenced by its successful integration with various LLMs, highlighting its potential for the future of interactive language models. |
| title | Empowering Language Models with Active Inquiry for Deeper Understanding |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2402.03719 |