为求何事询何人：基于多轮大语言模型交互的自适应群体咨询

摘要

在存在實際成本限制和數據缺失的情況下，要通過調查及其他集體評估方式獲取信息以降低對潛在群體屬性的不確定性，需要合理分配有限的提問資源。儘管大語言模型支持自然語言的適應性多輪交互，現有的大多數信息誘導方法僅針對固定受訪群體優化提問內容，既未在響應不完整時動態調整受訪者選擇策略，也未有效利用群體結構特徵。為解決這一侷限性，我們研究自適應群體誘導機制——一種在多輪交互中智能體根據明確的提詢問責與參與預算，自適應選擇問題與受訪者的框架。我們提出理論基礎完善的雙重架構：首先採用基於大語言模型的期望信息增益目標函數對候選問題進行評分，其次通過異構圖神經網絡傳播算法聚合已觀測響應與參與者屬性，實現缺失響應的估算並指導每輪的受訪者選擇。這種閉環流程既能查詢少量高信息量的個體，又能通過結構化相似性推斷群體層面的響應。在三個真實世界輿論數據集上的實驗表明，我們的方法在預算受限條件下持續提升群體響應預測精度，其中在僅使用10%受訪者預算時，CES數據集的相對增益超過12%。

English

Eliciting information to reduce uncertainty about latent group-level properties from surveys and other collective assessments requires allocating limited questioning effort under real costs and missing data. Although large language models enable adaptive, multi-turn interactions in natural language, most existing elicitation methods optimize what to ask with a fixed respondent pool, and do not adapt respondent selection or leverage population structure when responses are partial or incomplete. To address this gap, we study adaptive group elicitation, a multi-round setting where an agent adaptively selects both questions and respondents under explicit query and participation budgets. We propose a theoretically grounded framework that combines (i) an LLM-based expected information gain objective for scoring candidate questions with (ii) heterogeneous graph neural network propagation that aggregates observed responses and participant attributes to impute missing responses and guide per-round respondent selection. This closed-loop procedure queries a small, informative subset of individuals while inferring population-level responses via structured similarity. Across three real-world opinion datasets, our method consistently improves population-level response prediction under constrained budgets, including a >12% relative gain on CES at a 10% respondent budget.

为求何事询何人：基于多轮大语言模型交互的自适应群体咨询

Whom to Query for What: Adaptive Group Elicitation via Multi-Turn LLM Interactions

摘要

Support