Expanding the Set of Pragmatic Considerations in Conversational AI

S. M. Seals, Valerie L. Shalin
10/27/2023
cs.CL

No confident code implementation found for this paper.

Abstract

Despite considerable performance improvements, current conversational AI systems often fail to meet user expectations. We discuss several pragmatic limitations of current conversational AI systems. We illustrate pragmatic limitations with examples that are syntactically appropriate, but have clear pragmatic deficiencies. We label our complaints as "Turing Test Triggers" (TTTs) as they indicate where current conversational AI systems fall short compared to human behavior. We develop a taxonomy of pragmatic considerations intended to identify what pragmatic competencies a conversational AI system requires and discuss implications for the design and evaluation of conversational AI systems.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects

84% match2023

Discourse over Discourse: The Need for an Expanded Pragmatic Focus in Conversational AI

83% match2023

Let's Get Personal: Personal Questions Improve SocialBot Performance in the Alexa Prize

80% match2023

Revisiting the DARPA Communicator Data using Conversation Analysis

80% match2023

Conversational AI-Powered Design: ChatGPT as Designer, User, and Product

79% match2023

VakyArth: Evaluating Pragmatic Competence in LLMs across Indic Languages

78% match2026

Cite this paper

@article{seals2023expanding,
  title  = {Expanding the Set of Pragmatic Considerations in Conversational AI},
  author = {S. M. Seals and Valerie L. Shalin},
  year   = {2023},
  eprint = {2310.18435},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2310.18435v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.18435.svg)](https://codeofpaper.com/paper/2310.18435)

Discussion