arXiv cs.CL· Saber Zerhoudi·· 11 小时前AI 评分31
用户模拟器的共同偏差：模拟器分歧能否识别不可靠估计
Wrong Together: Shared Bias in User Simulation
AI 导读
研究用 6 个语言模型模拟器和 GlobalOpinionQA 中 12 个国家 60 个问题的现有回答，检验模拟器之间的分歧能否识别不可靠估计。分歧对组间差异的预测准确率高于单组回答比例（AUC 0.87 对 0.71），但模拟器共有的误差无法被该信号捕捉。用一组群体估计共同偏差并从另一组预测中减去后，预测误差下降而模拟器间分歧不变。
正文 · 原文
Abstract:User simulators generate responses in place of human participants, allowing researchers to estimate the result of a study. To use these estimates before collecting human responses, researchers need a way to assess their reliability. We test whether disagreement among simulators can identify unreliable estimates of a group's response proportions and of differences between groups. We evaluate this signal using 6 language-model simulators and existing GlobalOpinionQA responses for 60 questions in 12 countries. Disagreement predicts invalidity more accurately for differences between two groups than for a single group's response proportions (AUC 0.87 versus 0.71). Errors shared by the simulators remain invisible to this signal. When such an error affects both groups equally, it cancels in the comparison, helping explain the stronger result for group differences. We test this explanation by estimating the shared bias using one set of groups and subtracting it from predictions for a separate set. This correction reduces prediction error without changing disagreement among the simulators. In a retrospective analysis, we simulate referring the 20% of group comparisons with the greatest disagreement for human assessment. Among the remaining comparisons with a conclusive validity judgment, 54.8% are judged invalid, compared with 63.7% before referral.
| Subjects: | Computation and Language (cs.CL); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2611.01354 [cs.CL] |
| (or arXiv:2611.01354v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.01354 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | 40th Conference on Neural Information Processing Systems (NeurIPS 2026). Workshop: Grounded User Simulation for Model Evaluation and Training |
Submission history
From: Saber Zerhoudi [view email]
[v1]
Sat, 31 Oct 2026 23:48:40 UTC (222 KB)
来源：arXiv cs.CL · arxiv.org