mlsanityData to 7 Oct 2026

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

arXiv 2510.20039 ↗First posted 22 Oct 2025cs.HC cs.AI cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 22 of its 80 references that are in the map. First posted on arXiv 22 Oct 2025.

Builds on

22 of 80 references.

References · 22

  1. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  2. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  3. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  4. 2023Large Language Modelscited by 774
  5. 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 743
  6. 2024MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialoguescited by 247
  7. 2019Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Goodcited by 207
  8. 2025ELEPHANT: Measuring and understanding social sycophancy in LLMscited by 115
  9. 2023When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviourcited by 61
  10. 2024Prompt Design and Engineering: Introduction and Advanced Methodscited by 45
  11. 2022Let's Negotiate! A Survey of Negotiation Dialogue Systemscited by 31
  12. 2024Persuasion with Large Language Models: A Survey of Empirical Evidence, Study Methodologies, and Ethical Implicationscited by 30
10 more
  1. 2023How to Teach Programming in the AI Era? Using LLMs as a Teachable Agent for Debuggingcited by 29
  2. 2025A Survey on Multi-Turn Interaction Capabilities of Large Language Modelscited by 29
  3. 2025The Levers of Political Persuasion with Conversational AIcited by 19
  4. 2024User-Driven Value Alignment: Understanding Users' Perceptions and Strategies for Addressing Biased and Discriminatory Statements in AI Companionscited by 14
  5. 2025Epistemic Alignment: A Mediating Framework for User-LLM Knowledge Deliverycited by 14
  6. 2025Personalized Safety in LLMs: A Benchmark and A Planning-Based Agent Approachcited by 14
  7. 2024Exploring the Impact of AI Value Alignment in Collaborative Ideation: Effects on Perception, Ownership, and Outputcited by 12
  8. 2025A Framework to Assess the Persuasion Risks Large Language Model Chatbots Pose to Democratic Societiescited by 8
  9. 2024Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationshipscited by 7
  10. 2023MultiTurnCleanup: A Benchmark for Multi-Turn Spoken Conversational Transcript Cleanupcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2026Position: Anthropomorphic Misalignment Research Needs Stronger Evidencecited by 6
  2. 2026Attractor States Emerge in Multi-Turn LLM Conversationscited by 6
  3. 2026Feedback by Design: Understanding and Overcoming User Feedback Barriers in Conversational Agentscited by 4
  4. 2025Human-AI Interaction Alignment: Designing, Evaluating, and Evolving Value-Centered AI For Reciprocal Human-AI Futurescited by 0
  5. 2026Do LLM Agents Mirror Socio-Cognitive Effects in Power-Asymmetric Conversations?cited by 0