Reducing Confirmation Bias on Controversial Issues through LLM-Generated Multi-Persona Debates
cs.HC, cs.CY, cs.IR
Submitted: 2024-12-05
Updated: 2026-10-31
Terminology
Sources
- Out of One, Many: Using Language Models to Simulate Human Samples
- Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Prompting
- From Persona to Personalization: A Survey on Role-Playing Language Agents
- ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs
- A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
- Debating with More Persuasive LLMs Leads to More Truthful Answers
- Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate
- PersonaFlow: Designing LLM-Simulated Expert Perspectives for Enhanced Research Ideation
- Leveraging BERT for Extractive Text Summarization on Lectures
- Diverse, but Divisive: LLMs Can Exaggerate Gender Differences in Opinion Related to Harms of Misinformation
- Human-Centered Design Recommendations for LLM-as-a-Judge
- ChoiceMates: Supporting Unfamiliar Online Decision-Making with Multi-Agent Conversational Interactions
- Generative Agents: Interactive Simulacra of Human Behavior
- Some Observations on Fact-Checking Work with Implications for Computational Support
- Large Language Models for Data Annotation and Synthesis: A Survey
- Systematic Biases in LLM Simulations of Debates
- Is ChatGPT a Good NLG Evaluator? A Preliminary Study
Related papers
- EmoPhone: A Multi-Wave Dataset for In-the-Wild Mobile and Wearable Affect Sensing
- Tasteply: Externalizing Stable and Situational Preference as Manipulable Spatial Objects
- Shielded Trajectory Sampling for Personalized Relational Safety in Conversational AI
- From Tasks to Turns: Measuring Human Labor Contributions in Human-Agent Joint Production
- Reconstruction and Reflection of Positive Experiences through Resurfacing Laughter-indexed Everyday Moments
- LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems