Language Models in Dialogue: Conversational Maxims for Human-AI Interactions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Miehling, Erik, Nagireddy, Manish, Sattigeri, Prasanna, Daly, Elizabeth M., Piorkowski, David, Richards, John T.
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