Inductive-Deductive Strategy Reuse for Multi-Turn Instructional Dialogues
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_ | 1866912049170219008 |
|---|---|
| author | Ou, Jiao Wu, Jiayu Liu, Che Zhang, Fuzheng Zhang, Di Gai, Kun |
| author_facet | Ou, Jiao Wu, Jiayu Liu, Che Zhang, Fuzheng Zhang, Di Gai, Kun |
| contents | Aligning large language models (LLMs) with human expectations requires high-quality instructional dialogues, which usually require instructions that are diverse and in-depth. Existing methods leverage two LLMs to interact for automatic collection: one simulating a user to pose instructions, and the other acting as a system agent to respond. However, these user simulators struggle to model the rules behind how dialogues can pose different instructions without explicit guidance, resulting in general instructions. In this paper, we propose to explicitly capture the complex rules to help the user simulator pose diverse and in-depth instruction. Specifically, we first induce high-level instruction strategies from various real instruction dialogues serving as rules. Afterward, different possible strategies are applied to the newly given dialogue scenario deductively to pose various instructions. Experimental results show that our method can generate diverse and in-depth instructions. The constructed multi-turn instructional dialogues can outperform competitive baselines on the downstream chat model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_11095 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Inductive-Deductive Strategy Reuse for Multi-Turn Instructional Dialogues Ou, Jiao Wu, Jiayu Liu, Che Zhang, Fuzheng Zhang, Di Gai, Kun Computation and Language Artificial Intelligence Aligning large language models (LLMs) with human expectations requires high-quality instructional dialogues, which usually require instructions that are diverse and in-depth. Existing methods leverage two LLMs to interact for automatic collection: one simulating a user to pose instructions, and the other acting as a system agent to respond. However, these user simulators struggle to model the rules behind how dialogues can pose different instructions without explicit guidance, resulting in general instructions. In this paper, we propose to explicitly capture the complex rules to help the user simulator pose diverse and in-depth instruction. Specifically, we first induce high-level instruction strategies from various real instruction dialogues serving as rules. Afterward, different possible strategies are applied to the newly given dialogue scenario deductively to pose various instructions. Experimental results show that our method can generate diverse and in-depth instructions. The constructed multi-turn instructional dialogues can outperform competitive baselines on the downstream chat model. |
| title | Inductive-Deductive Strategy Reuse for Multi-Turn Instructional Dialogues |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2404.11095 |