Rethinking the Evaluation and Optimization of LLM-Based Social Simulation

• URL: http://arxiv.org/abs/2608.19689v1
• Date: Thu, 20 Aug 2026 06:26:03 GMT
• Title: Rethinking the Evaluation and Optimization of LLM-Based Social Simulation
• Abstract summary: We use the subjectivity coefficient to analyze how accuracy-based evaluation and hard-label training fail as subjectivity grows.<n>We construct SUBJSIM, a benchmark of 19,300 contexts covering 193 annotators and 100 subjective questions.<n>Results on SUBJSIM demonstrate the advantages of our method.
• Score: 56.18577997572273
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM-based social simulation is a promising complement to traditional methods such as surveys and behavioral experiments. A core question is how to evaluate the fidelity of LLM-simulated human behavior and optimize LLMs toward it. Prevailing practice evaluates by accuracy, checking whether the model selects the single response observed from a human, and trains the LLM to reproduce this hard label. However, human behavior is inherently subjective: the same person in the same situation may reasonably act differently, so an observed response is only one draw from an underlying response distribution, rendering accuracy-based evaluation unreliable and hard-label training misleading. To address these problems, we first introduce the subjectivity coefficient, an entropy-based quantity distinguishing objective tasks such as coding from subjective ones such as social simulation, and use it to systematically analyze how accuracy-based evaluation and hard-label training fail as subjectivity grows. Based on the subjectivity coefficient, we propose Subjectivity-Adaptive soft-Label Training (SALT): it pools observed outputs from semantically nearby inputs into soft distributional labels, with an aggregation radius adapted to the estimated subjectivity of each input; in the near-objective limit the neighborhood shrinks, so SALT naturally falls back to standard single-label training. Moreover, since existing datasets record only single observed responses and cannot support distributional evaluation, we construct SUBJSIM, a benchmark of 19,300 contexts covering 193 annotators and 100 subjective questions. Since real-world data typically provide only a single observation per input, our experiments train models from single observed outputs while evaluating them against the full response distributions, verifying feasibility in realistic settings. Results on SUBJSIM demonstrate the advantages of our method.

Related papers

• Beyond Averages: Evaluating LLMs on Human Survey Replication at the Distributional Level [8.995779634140495]
  We evaluate survey replication using a non-public 2010 consumer choice experiment on Korean instant noodle purchases.<n>We compare human and LLM responses at mean-level, pattern, and distributional alignment, and against reference baselines from the human data alone.
  arXiv  Detail & Related papers  (2026-06-08T04:22:15Z)
• Individual Turing Test: A Case Study of LLM-based Simulation Using Longitudinal Personal Data [54.145424717168794]
  Large Language Models (LLMs) have demonstrated remarkable human-like capabilities, yet their ability to replicate a specific individual remains under-explored.<n>This paper presents a case study to investigate LLM-based individual simulation with a volunteer-contributed archive of private messaging history spanning over ten years.<n>We propose the "Individual Turing Test" to evaluate whether acquaintances of the volunteer can correctly identify which response in a multi-candidate pool most plausibly comes from the volunteer.
  arXiv  Detail & Related papers  (2026-03-01T21:46:27Z)
• Overstating Attitudes, Ignoring Networks: LLM Biases in Simulating Misinformation Susceptibility [7.616305266104683]
  Large language models (LLMs) are increasingly used as proxies for human judgment in computational social science.<n>We test whether LLM-simulated survey respondents can reproduce human patterns of misinformation belief and sharing.
  arXiv  Detail & Related papers  (2026-02-04T15:48:05Z)
• Uncertainty Quantification for Large Language Model Reward Learning under Heterogeneous Human Feedback [8.538830579425147]
  We study estimation and statistical reward models used in aligning large language (LLMs)<n>A key component of LLM alignment is reinforcement learning from human feedback.
  arXiv  Detail & Related papers  (2025-12-02T20:22:25Z)
• IROTE: Human-like Traits Elicitation of Large Language Model via In-Context Self-Reflective Optimization [66.6349183886101]
  We propose IROTE, a novel in-context method for stable and transferable trait elicitation.<n>We show that one single IROTE-generated self-reflection can induce LLMs' stable impersonation of the target trait across diverse downstream tasks.
  arXiv  Detail & Related papers  (2025-08-12T08:04:28Z)
• Beyond the Singular: The Essential Role of Multiple Generations in Effective Benchmark Evaluation and Analysis [10.133537818749291]
  Large language models (LLMs) have demonstrated significant utilities in real-world applications.<n> Benchmark evaluations are crucial for assessing the capabilities of LLMs.
  arXiv  Detail & Related papers  (2025-02-13T03:43:33Z)
• Uncertainty Aware Learning for Language Model Alignment [97.36361196793929]
  We propose uncertainty-aware learning (UAL) to improve the model alignment of different task scenarios. We implement UAL in a simple fashion -- adaptively setting the label smoothing value of training according to the uncertainty of individual samples. Experiments on widely used benchmarks demonstrate that our UAL significantly and consistently outperforms standard supervised fine-tuning.
  arXiv  Detail & Related papers  (2024-06-07T11:37:45Z)
• Evaluating Generative Language Models in Information Extraction as Subjective Question Correction [49.729908337372436]
  We propose a new evaluation method, SQC-Score. Inspired by the principles in subjective question correction, we propose a new evaluation method, SQC-Score. Results on three information extraction tasks show that SQC-Score is more preferred by human annotators than the baseline metrics.
  arXiv  Detail & Related papers  (2024-04-04T15:36:53Z)
• Bring Your Own Data! Self-Supervised Evaluation for Large Language Models [52.15056231665816]
  We propose a framework for self-supervised evaluation of Large Language Models (LLMs) We demonstrate self-supervised evaluation strategies for measuring closed-book knowledge, toxicity, and long-range context dependence. We find strong correlations between self-supervised and human-supervised evaluations.
  arXiv  Detail & Related papers  (2023-06-23T17:59:09Z)

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.