Language Models in Dialogue: Conversational Maxims for Human-AI Interactions
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_ | 1866909229202276352 |
|---|---|
| author | Miehling, Erik Nagireddy, Manish Sattigeri, Prasanna Daly, Elizabeth M. Piorkowski, David Richards, John T. |
| author_facet | Miehling, Erik Nagireddy, Manish Sattigeri, Prasanna Daly, Elizabeth M. Piorkowski, David Richards, John T. |
| contents | Modern language models, while sophisticated, exhibit some inherent shortcomings, particularly in conversational settings. We claim that many of the observed shortcomings can be attributed to violation of one or more conversational principles. By drawing upon extensive research from both the social science and AI communities, we propose a set of maxims -- quantity, quality, relevance, manner, benevolence, and transparency -- for describing effective human-AI conversation. We first justify the applicability of the first four maxims (from Grice) in the context of human-AI interactions. We then argue that two new maxims, benevolence (concerning the generation of, and engagement with, harmful content) and transparency (concerning recognition of one's knowledge boundaries, operational constraints, and intents), are necessary for addressing behavior unique to modern human-AI interactions. We evaluate the degree to which various language models are able to understand these maxims and find that models possess an internal prioritization of principles that can significantly impact their ability to interpret the maxims accurately. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_15115 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Language Models in Dialogue: Conversational Maxims for Human-AI Interactions Miehling, Erik Nagireddy, Manish Sattigeri, Prasanna Daly, Elizabeth M. Piorkowski, David Richards, John T. Computation and Language Artificial Intelligence Human-Computer Interaction Modern language models, while sophisticated, exhibit some inherent shortcomings, particularly in conversational settings. We claim that many of the observed shortcomings can be attributed to violation of one or more conversational principles. By drawing upon extensive research from both the social science and AI communities, we propose a set of maxims -- quantity, quality, relevance, manner, benevolence, and transparency -- for describing effective human-AI conversation. We first justify the applicability of the first four maxims (from Grice) in the context of human-AI interactions. We then argue that two new maxims, benevolence (concerning the generation of, and engagement with, harmful content) and transparency (concerning recognition of one's knowledge boundaries, operational constraints, and intents), are necessary for addressing behavior unique to modern human-AI interactions. We evaluate the degree to which various language models are able to understand these maxims and find that models possess an internal prioritization of principles that can significantly impact their ability to interpret the maxims accurately. |
| title | Language Models in Dialogue: Conversational Maxims for Human-AI Interactions |
| topic | Computation and Language Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2403.15115 |