Towards Dialogues for Joint Human-AI Reasoning and Value Alignment
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909212206956544 |
|---|---|
| author | Bezou-Vrakatseli, Elfia Cocarascu, Oana Modgil, Sanjay |
| author_facet | Bezou-Vrakatseli, Elfia Cocarascu, Oana Modgil, Sanjay |
| contents | We argue that enabling human-AI dialogue, purposed to support joint reasoning (i.e., 'inquiry'), is important for ensuring that AI decision making is aligned with human values and preferences. In particular, we point to logic-based models of argumentation and dialogue, and suggest that the traditional focus on persuasion dialogues be replaced by a focus on inquiry dialogues, and the distinct challenges that joint inquiry raises. Given recent dramatic advances in the performance of large language models (LLMs), and the anticipated increase in their use for decision making, we provide a roadmap for research into inquiry dialogues for supporting joint human-LLM reasoning tasks that are ethically salient, and that thereby require that decisions are value aligned. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_18073 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Dialogues for Joint Human-AI Reasoning and Value Alignment Bezou-Vrakatseli, Elfia Cocarascu, Oana Modgil, Sanjay Artificial Intelligence We argue that enabling human-AI dialogue, purposed to support joint reasoning (i.e., 'inquiry'), is important for ensuring that AI decision making is aligned with human values and preferences. In particular, we point to logic-based models of argumentation and dialogue, and suggest that the traditional focus on persuasion dialogues be replaced by a focus on inquiry dialogues, and the distinct challenges that joint inquiry raises. Given recent dramatic advances in the performance of large language models (LLMs), and the anticipated increase in their use for decision making, we provide a roadmap for research into inquiry dialogues for supporting joint human-LLM reasoning tasks that are ethically salient, and that thereby require that decisions are value aligned. |
| title | Towards Dialogues for Joint Human-AI Reasoning and Value Alignment |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2405.18073 |