Research map / Large language models / Alignment and preferences
Can LLMs Truly Embody Human Personality? Analyzing AI and Human Behavior Alignment in Dispute Resolution
Deuksin Kwon, Kaleen Shrestha, Bin Han, Spencer Lin, James Hale, Jonathan Gratch, Maja Mataric, Gale M. Lucas
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| prompt the LLM with higher agreeableness | GPT-4o mini · L2L dispute negotiation | final score: B=-4.38 | Hurt |
| prompt the LLM with higher agreeableness | Claude Sonnet 3.7 · L2L dispute negotiation | final score: B=-2.50 | Hurt |
| prompt the LLM with higher agreeableness | Gemini 2.0 Flash · L2L dispute negotiation | final score: B=-4.48 | Hurt |
| assign higher self extraversion | GPT-4o mini · L2L dispute negotiation | final score: B=1.67 | Improved |
| higher self neuroticism in human participants | KODIS humans · KODIS dispute | offer acceptance: B=-0.26 | Hurt |
| personality-prompted LLMs versus humans on score | GPT-4o mini, Claude, Gemini · KODIS vs L2L | score effects of traits | Mixed |
| prompt LLM with self extraversion for competitive strategy ratio | GPT-4o mini and Gemini · KODIS vs L2L | competitive IRP ratio: B=0.95 and B=1.07 vs human B=1.74 | Improved |
| personality prompting for cooperative reciprocity | GPT-4o mini, Gemini, Claude · KODIS vs L2L | cooperative reciprocity alignment | Hurt |
| personality prompting for competitive reciprocity | Gemini and Claude · KODIS vs L2L | competitive reciprocity alignment | Improved |
| personality prompting for escalation response | Gemini · KODIS vs L2L | escalation alignment | Mixed |
| role-dependent self agreeableness on acceptance | GPT-4o mini · KODIS vs L2L buyer role | offer acceptance: B=-0.14 vs human B=-0.39 | Improved |
| add self agreeableness for escalation | Claude Sonnet 3.7 · L2L dispute negotiation | escalation ratio: B=-2.45 | Hurt |
Closest papers by meaning
- EAI: Emotional Decision-Making of LLMs in Strategic Games and Ethical Dilemmas (NeurIPS 2024 · similarity 0.89)
- Open Models, Closed Minds? On Agents Capabilities in Mimicking Human Personalities through Open Large Language Models (AAAI 2025 · similarity 0.89)
- Personality Alignment of Large Language Models (ICLR 2025 · similarity 0.88)
- Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior (NeurIPS 2026 · similarity 0.87)
- Apathetic or Empathetic? Evaluating LLMs' Emotional Alignments with Humans (NeurIPS 2024 · similarity 0.87)
- How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis (ICML 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
