# Evaluating LLM-Simulated Conversations in Modeling Inconsistent and Uncollaborative Behaviors in Human Social Interaction

arXiv: https://arxiv.org/abs/2603.17094 · HTML: https://mlsanity.com/paper/2603.17094/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 56 references that are in the map.
- First posted on arXiv 17 Mar 2026.

## Builds on (most cited first, 18 of 18)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://mlsanity.com/paper/2310.11667/) (2023)
- [QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization](https://mlsanity.com/paper/2104.05938/) (2021)
- [Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents](https://mlsanity.com/paper/2404.16698/) (2024)
- [CollabLLM: From Passive Responders to Active Collaborators](https://mlsanity.com/paper/2502.00640/) (2025)
- [Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debate](https://mlsanity.com/paper/2305.13160/) (2023)
- [AugESC: Dialogue Augmentation with Large Language Models for Emotional Support Conversation](https://mlsanity.com/paper/2202.13047/) (2022)
- [Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMs](https://mlsanity.com/paper/2403.05020/) (2024)
- [Conversational flow in Oxford-style debates](https://mlsanity.com/paper/1604.03114/) (2016)
- [NormDial: A Comparable Bilingual Synthetic Dialog Dataset for Modeling Social Norm Adherence and Violation](https://mlsanity.com/paper/2310.14563/) (2023)
- [ShareChat: A Dataset of Chatbot Conversations in the Wild](https://mlsanity.com/paper/2512.17843/) (2025)
- [Cohesive Conversations: Enhancing Authenticity in Multi-Agent Simulated Dialogues](https://mlsanity.com/paper/2407.09897/) (2024)
- [Who Speaks Next? Multi-party AI Discussion Leveraging the Systematics of Turn-taking in Murder Mystery Games](https://mlsanity.com/paper/2412.04937/) (2024)
- [Multi-Party Supervised Fine-tuning of Language Models for Multi-Party Dialogue Generation](https://mlsanity.com/paper/2412.05342/) (2024)
- [Topic-Conversation Relevance (TCR) Dataset and Benchmarks](https://mlsanity.com/paper/2411.00038/) (2024)
- [ProMediate: A Socio-cognitive framework for evaluating proactive agents in multi-party negotiation](https://mlsanity.com/paper/2510.25224/) (2025)

## Abstract (arXiv)

Simulating human conversations using large language models (LLMs) has emerged as a scalable methodology for modeling human social interaction. This paper reconsiders the evaluation of simulated conversations by explicitly recognizing that human conversations inherently involve inconsistent and uncollaborative behaviors, such as misunderstandings and interruptions. Since these behaviors contribute to the complexity of human social interaction, we argue that LLM-simulated conversations should reproduce them at frequencies comparable to those observed in human conversations. To support a detailed and interpretable evaluation of these behaviors, we introduce CoCoEval, a framework consisting of an evaluation scheme based on turn-level detection of 10 types of inconsistent and uncollaborative behaviors and a benchmark for simulating conversations in professional scenarios involving collaboration and conflict. Using CoCoEval, we compare human conversations with those simulated by GPT-4.1, GPT-5.1, and Claude Opus 4. The results show that (1) LLM-simulated conversations exhibit far fewer inconsistent and uncollaborative behaviors than human conversations under vanilla prompting, and (2) prompt engineering and supervised fine-tuning do not provide reliable control over these behaviors, often leading to the overproduction of specific behaviors. CoCoEval identifies gaps between human and LLM-simulated conversations that are not captured by conventional evaluation based on conversation-level Likert scales, raising concerns about the use of LLMs as proxies for human social interaction.