Skip to main navigation Skip to search Skip to main content

Short Prompts, Long Replies: What Alignment Looks Like in Human–AI Dialogue

  • Daniel Jiandong SHEN*
  • , Renia LOPEZ-OZIEBLO
  • , Paolo MENGONI
  • , Kristen Yuanxi LI
  • , Aru NURGISSAYEVA
  • , Paulina Pui Yun WONG
  • *Corresponding author for this work

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Referred Conference Paper › peer-review

Abstract

The purpose of this study is to examine how lexical and stylistic alignment appear in adjacent human–AI turns under strong role and length asymmetry in an instructional setting. Human–AI dialogue is often evaluated using conversation-level similarity measures, but these can hide how coordination is produced turn by turn. We analyzed written brainstorming dialogues from 88 students interacting with generative AI advisor avatars (967 turns). Using an R pipeline, turns were cleaned, lemmatized, and POS-tagged with UDPipe. Adjacent student–AI pairs were then scored for lexical overlap (Jaccard) and stylistic alignment (LSM). Lexical overlap was consistently low (content-lemma Jaccard M = 0.0639; bigram Jaccard M = 0.0293), consistent with limited opportunity for exact reuse when short student inputs are followed by longer AI responses. In contrast, LSM was moderate and variable (M = 0.215, SD = 0.214), and only moderately related to lexical overlap (r = .48), indicating that coordination can be expressed through framing even when topical words are not repeated. Both lexical and stylistic alignment were strongest early and declined over interactional time, suggesting reduced need for overt grounding once goals and roles stabilize. These findings show that low lexical overlap does not imply weak coordination and support turn-level, multi-dimensional analysis.

Original languageEnglish
Title of host publicationAdvances and Trends in Artificial Intelligence: Theory and Applications : 39th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2026, Proceedings, Part I
EditorsHamido FUJITA, Ali SELAMAT, Masitah GHAZALI, Moonis ALI
PublisherSpringer Science and Business Media Deutschland GmbH
Pages39-49
Number of pages11
ISBN (Print)9789819228843
DOIs
Publication statusE-pub ahead of print - 16 Jul 2026
Event39th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2026 - Kuala Lumpur, Malaysia
Duration: 6 Jul 2026 → 8 Jul 2026

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume16614
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference39th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2026
Country/TerritoryMalaysia
CityKuala Lumpur
Period6/07/26 → 8/07/26

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2027.

Funding

This study was funded by Lingnan University, Hong Kong, through the Fund for Innovative Technology-in-Education (FITE) of the University Grants Committee (Project Code: 120042) and partly funded by the Faculty of Humanities of The Hong Kong Polytechnic University, FITE project 04-2025.

Keywords

  • conversational alignment
  • dyadic analysis
  • human–AI dialogue
  • lexical overlap
  • linguistic style matching

Fingerprint

Dive into the research topics of 'Short Prompts, Long Replies: What Alignment Looks Like in Human–AI Dialogue'. Together they form a unique fingerprint.

Cite this