The Adaptation Paradox: Agency vs. Mimicry in Companion Chatbots

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Brandt, T. James, Wang, Cecilia Xi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918141619077120
author Brandt, T. James
Wang, Cecilia Xi
author_facet Brandt, T. James
Wang, Cecilia Xi
contents Generative AI powers a growing wave of companion chatbots, yet principles for fostering genuine connection remain unsettled. We test two routes: visible user authorship versus covert language-style mimicry. In a preregistered 3x2 experiment (N = 162), we manipulated user-controlled avatar generation (none, premade, user-generated) and Language Style Matching (LSM) (static vs. adaptive). Generating an avatar boosted rapport ($ω^2$ = .040, p = .013), whereas adaptive LSM underperformed static style on personalization and satisfaction (d = 0.35, p = .009) and was paradoxically judged less adaptive (t = 3.07, p = .003, d = 0.48). We term this an Adaptation Paradox: synchrony erodes connection when perceived as incoherent, destabilizing persona. To explain, we propose a stability-and-legibility account: visible authorship fosters natural interaction, while covert mimicry risks incoherence. Our findings suggest designers should prioritize legible, user-driven personalization and limit stylistic shifts rather than rely on opaque mimicry.
format Preprint
id arxiv_https___arxiv_org_abs_2509_12525
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Adaptation Paradox: Agency vs. Mimicry in Companion Chatbots
Brandt, T. James
Wang, Cecilia Xi
Human-Computer Interaction
Computation and Language
H.5.2; I.2.7
Generative AI powers a growing wave of companion chatbots, yet principles for fostering genuine connection remain unsettled. We test two routes: visible user authorship versus covert language-style mimicry. In a preregistered 3x2 experiment (N = 162), we manipulated user-controlled avatar generation (none, premade, user-generated) and Language Style Matching (LSM) (static vs. adaptive). Generating an avatar boosted rapport ($ω^2$ = .040, p = .013), whereas adaptive LSM underperformed static style on personalization and satisfaction (d = 0.35, p = .009) and was paradoxically judged less adaptive (t = 3.07, p = .003, d = 0.48). We term this an Adaptation Paradox: synchrony erodes connection when perceived as incoherent, destabilizing persona. To explain, we propose a stability-and-legibility account: visible authorship fosters natural interaction, while covert mimicry risks incoherence. Our findings suggest designers should prioritize legible, user-driven personalization and limit stylistic shifts rather than rely on opaque mimicry.
title The Adaptation Paradox: Agency vs. Mimicry in Companion Chatbots
topic Human-Computer Interaction
Computation and Language
H.5.2; I.2.7
url https://arxiv.org/abs/2509.12525