Beyond One-Way Influence: Bidirectional Opinion Dynamics in Multi-Turn Human-LLM Interactions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Yuyang, Guo, Longjie, Wu, Yuchen, Caliskan, Aylin, Mitra, Tanu, Shen, Hua
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909864714829824
author Jiang, Yuyang
Guo, Longjie
Wu, Yuchen
Caliskan, Aylin
Mitra, Tanu
Shen, Hua
author_facet Jiang, Yuyang
Guo, Longjie
Wu, Yuchen
Caliskan, Aylin
Mitra, Tanu
Shen, Hua
contents Large language model (LLM)-powered chatbots are increasingly used for opinion exploration. Prior research examined how LLMs alter user views, yet little work extended beyond one-way influence to address how user input can affect LLM responses and how such bi-directional influence manifests throughout the multi-turn conversations. This study investigates this dynamic through 50 controversial-topic discussions with participants (N=266) across three conditions: static statements, standard chatbot, and personalized chatbot. Results show that human opinions barely shifted, while LLM outputs changed more substantially, narrowing the gap between human and LLM stance. Personalization amplified these shifts in both directions compared to the standard setting. Analysis of multi-turn conversations further revealed that exchanges involving participants' personal stories were most likely to trigger stance changes for both humans and LLMs. Our work highlights the risk of over-alignment in human-LLM interaction and the need for careful design of personalized chatbots to more thoughtfully and stably align with users.
format Preprint
id arxiv_https___arxiv_org_abs_2510_20039
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond One-Way Influence: Bidirectional Opinion Dynamics in Multi-Turn Human-LLM Interactions
Jiang, Yuyang
Guo, Longjie
Wu, Yuchen
Caliskan, Aylin
Mitra, Tanu
Shen, Hua
Human-Computer Interaction
Artificial Intelligence
Computation and Language
Computers and Society
Large language model (LLM)-powered chatbots are increasingly used for opinion exploration. Prior research examined how LLMs alter user views, yet little work extended beyond one-way influence to address how user input can affect LLM responses and how such bi-directional influence manifests throughout the multi-turn conversations. This study investigates this dynamic through 50 controversial-topic discussions with participants (N=266) across three conditions: static statements, standard chatbot, and personalized chatbot. Results show that human opinions barely shifted, while LLM outputs changed more substantially, narrowing the gap between human and LLM stance. Personalization amplified these shifts in both directions compared to the standard setting. Analysis of multi-turn conversations further revealed that exchanges involving participants' personal stories were most likely to trigger stance changes for both humans and LLMs. Our work highlights the risk of over-alignment in human-LLM interaction and the need for careful design of personalized chatbots to more thoughtfully and stably align with users.
title Beyond One-Way Influence: Bidirectional Opinion Dynamics in Multi-Turn Human-LLM Interactions
topic Human-Computer Interaction
Artificial Intelligence
Computation and Language
Computers and Society
url https://arxiv.org/abs/2510.20039