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

• URL: http://arxiv.org/abs/2603.17094v1
• Date: Tue, 17 Mar 2026 19:29:50 GMT
• Title: Evaluating LLM-Simulated Conversations in Modeling Inconsistent and Uncollaborative Behaviors in Human Social Interaction
• Abstract summary: Simulating human conversations using large language models (LLMs) has emerged as a scalable methodology for modeling human social interaction.<n>We introduce CoCoEval, an evaluation framework that analyzes LLM-simulated conversations by detecting 10 types of inconsistent and uncollaborative behaviors.<n>Our analysis shows that under vanilla prompting, LLM-simulated conversations exhibit far fewer inconsistent and uncollaborative behaviors than human conversations.
• Score: 21.123771789383323
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Simulating human conversations using large language models (LLMs) has emerged as a scalable methodology for modeling human social interaction. However, simulating human conversations is challenging because they inherently involve inconsistent and uncollaborative behaviors, such as misunderstandings and interruptions. Analysis comparing inconsistent and uncollaborative behaviors in human- and LLM-generated conversations remains limited, although reproducing these behaviors is integral to simulating human-like and complex social interaction. In this work, we introduce CoCoEval, an evaluation framework that analyzes LLM-simulated conversations by detecting 10 types of inconsistent and uncollaborative behaviors at the turn level using an LLM-as-a-Judge. Using CoCoEval, we evaluate GPT-4.1, GPT-5.1, and Claude Opus 4 by comparing the frequencies of detected behaviors in conversations simulated by each model and in human conversations across academic, business, and governmental meetings, as well as debates. Our analysis shows that (1) under vanilla prompting, LLM-simulated conversations exhibit far fewer inconsistent and uncollaborative behaviors than human conversations; (2) prompt engineering does not provide reliable control over these behaviors, as our results show that different prompts lead to their under- or overproduction; and (3) supervised fine-tuning on human conversations can lead LLMs to overproduce a narrow set of behaviors, such as repetition. Our findings highlight the difficulty of simulating human conversations, raising concerns about the use of LLMs as a proxy for human social interaction.

Related papers

• Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior [58.538864650160406]
  We run experiments across four behavioral tasks and 11 frontier LLMs.<n>We find that SR-behavior coherence exists but is selective.<n>These findings suggest that coarse personality frameworks may not be the best tools for testing deployment behavior.
  arXiv  Detail & Related papers  (2026-06-10T22:28:53Z)
• Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts [9.62483752303596]
  Large language models (LLMs) exhibit a wide range of human-like behaviors.<n>We use a multi-dimensional analysis of the prevalence, potential effects, and controllability of these behaviors using LLM-as-a-judge and human evaluation.<n>We show that system prompting can control these behaviors, though it requires careful evaluation to avoid unintended effects.
  arXiv  Detail & Related papers  (2026-05-07T18:58:50Z)
• Can LLMs Truly Embody Human Personality? Analyzing AI and Human Behavior Alignment in Dispute Resolution [7.599497643290519]
  Large language models (LLMs) are increasingly used to simulate human behavior in social settings.<n>It remains unclear whether these simulations reproduce the personality-behavior patterns observed in humans.
  arXiv  Detail & Related papers  (2026-02-07T07:20:24Z)
• Emulating Aggregate Human Choice Behavior and Biases with GPT Conversational Agents [0.48439699124726004]
  Large language models (LLMs) have been shown to reproduce well-known biases.<n>We adapted three well-established decision scenarios into a conversational setting and conducted a human experiment.<n>We found notable differences between models in how they aligned human behavior.
  arXiv  Detail & Related papers  (2026-02-05T12:33:05Z)
• Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning [52.07170679746533]
  Large Language Models (LLMs) are increasingly used to simulate human users in interactive settings such as therapy, education, and social role-play.<n>We introduce a unified framework for evaluating and improving persona consistency in LLM-generated dialogue.<n>We define three automatic metrics: prompt-to-line consistency, line-to-line consistency, and Q&A consistency, that capture different types of persona drift and validate each against human annotations.
  arXiv  Detail & Related papers  (2025-10-31T19:40:41Z)
• TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation [55.55404595177229]
  Large Language Models (LLMs) are exhibiting emergent human-like abilities.<n>TwinVoice is a benchmark for assessing persona simulation across diverse real-world contexts.
  arXiv  Detail & Related papers  (2025-10-29T14:00:42Z)
• Social Simulations with Large Language Model Risk Utopian Illusion [61.358959720048354]
  We introduce a systematic framework for analyzing large language models' behavior in social simulation.<n>Our approach simulates multi-agent interactions through chatroom-style conversations and analyzes them across five linguistic dimensions.<n>Our findings reveal that LLMs do not faithfully reproduce genuine human behavior but instead reflect overly idealized versions of it.
  arXiv  Detail & Related papers  (2025-10-24T06:08:41Z)
• How large language models judge and influence human cooperation [82.07571393247476]
  We assess how state-of-the-art language models judge cooperative actions.<n>We observe a remarkable agreement in evaluating cooperation against good opponents.<n>We show that the differences revealed between models can significantly impact the prevalence of cooperation.
  arXiv  Detail & Related papers  (2025-06-30T09:14:42Z)
• SocialEval: Evaluating Social Intelligence of Large Language Models [70.90981021629021]
  Social Intelligence (SI) equips humans with interpersonal abilities to behave wisely in navigating social interactions to achieve social goals.<n>This presents an operational evaluation paradigm: outcome-oriented goal achievement evaluation and process-oriented interpersonal ability evaluation.<n>We propose SocialEval, a script-based bilingual SI benchmark, integrating outcome- and process-oriented evaluation by manually crafting narrative scripts.
  arXiv  Detail & Related papers  (2025-06-01T08:36:51Z)
• Word Synchronization Challenge: A Benchmark for Word Association Responses for LLMs [4.352318127577628]
  This paper introduces the Word Synchronization Challenge, a novel benchmark to evaluate large language models (LLMs) in Human-Computer Interaction (HCI)<n>This benchmark uses a dynamic game-like framework to test LLMs ability to mimic human cognitive processes through word associations.
  arXiv  Detail & Related papers  (2025-02-12T11:30:28Z)
• The Machine Psychology of Cooperation: Can GPT models operationalise prompts for altruism, cooperation, competitiveness and selfishness in economic games? [0.0]
  We investigated the capability of the GPT-3.5 large language model (LLM) to operationalize natural language descriptions of cooperative, competitive, altruistic, and self-interested behavior. We used a prompt to describe the task environment using a similar protocol to that used in experimental psychology studies with human subjects. Our results provide evidence that LLMs can, to some extent, translate natural language descriptions of different cooperative stances into corresponding descriptions of appropriate task behaviour.
  arXiv  Detail & Related papers  (2023-05-13T17:23:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.