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

arXiv: https://arxiv.org/abs/2510.20039 · HTML: https://mlsanity.com/paper/2510.20039/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 80 references that are in the map.
- First posted on arXiv 22 Oct 2025.

## Builds on (most cited first, 22 of 22)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues](https://mlsanity.com/paper/2402.14762/) (2024)
- [Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good](https://mlsanity.com/paper/1906.06725/) (2019)
- [ELEPHANT: Measuring and understanding social sycophancy in LLMs](https://mlsanity.com/paper/2505.13995/) (2025)
- [When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour](https://mlsanity.com/paper/2311.09410/) (2023)
- [Prompt Design and Engineering: Introduction and Advanced Methods](https://mlsanity.com/paper/2401.14423/) (2024)
- [Persuasion with Large Language Models: A Survey of Empirical Evidence, Study Methodologies, and Ethical Implications](https://mlsanity.com/paper/2411.06837/) (2024)
- [Let's Negotiate! A Survey of Negotiation Dialogue Systems](https://mlsanity.com/paper/2212.09072/) (2022)
- [How to Teach Programming in the AI Era? Using LLMs as a Teachable Agent for Debugging](https://mlsanity.com/paper/2310.05292/) (2023)
- [A Survey on Multi-Turn Interaction Capabilities of Large Language Models](https://mlsanity.com/paper/2501.09959/) (2025)
- [The Levers of Political Persuasion with Conversational AI](https://mlsanity.com/paper/2507.13919/) (2025)
- [Personalized Safety in LLMs: A Benchmark and A Planning-Based Agent Approach](https://mlsanity.com/paper/2505.18882/) (2025)
- [User-Driven Value Alignment: Understanding Users' Perceptions and Strategies for Addressing Biased and Discriminatory Statements in AI Companions](https://mlsanity.com/paper/2409.00862/) (2024)
- [Epistemic Alignment: A Mediating Framework for User-LLM Knowledge Delivery](https://mlsanity.com/paper/2504.01205/) (2025)
- [Exploring the Impact of AI Value Alignment in Collaborative Ideation: Effects on Perception, Ownership, and Output](https://mlsanity.com/paper/2402.12814/) (2024)
- [A Framework to Assess the Persuasion Risks Large Language Model Chatbots Pose to Democratic Societies](https://mlsanity.com/paper/2505.00036/) (2025)
- [Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationships](https://mlsanity.com/paper/2407.12543/) (2024)
- [MultiTurnCleanup: A Benchmark for Multi-Turn Spoken Conversational Transcript Cleanup](https://mlsanity.com/paper/2305.12029/) (2023)

## Built on by (most cited first, 6 of 6)

- [Position: Anthropomorphic Misalignment Research Needs Stronger Evidence](https://mlsanity.com/paper/2606.07612/) (2026)
- [Attractor States Emerge in Multi-Turn LLM Conversations](https://mlsanity.com/paper/2606.30571/) (2026)
- [Feedback by Design: Understanding and Overcoming User Feedback Barriers in Conversational Agents](https://mlsanity.com/paper/2602.01405/) (2026)
- [Human-AI Interaction Alignment: Designing, Evaluating, and Evolving Value-Centered AI For Reciprocal Human-AI Futures](https://mlsanity.com/paper/2512.21551/) (2025)
- [Do LLM Agents Mirror Socio-Cognitive Effects in Power-Asymmetric Conversations?](https://mlsanity.com/paper/2605.17694/) (2026)
- [The AI's Poker Face: Contrasting Persuasion and Sycophancy in Voice-Based Multi-Turn Conversations](https://mlsanity.com/paper/2610.14124/) (2026)

## 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.