Whom to Query for What: Adaptive Group Elicitation via Multi-Turn LLM Interactions
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917275634761728 |
|---|---|
| author | Ding, Ruomeng Gao, Tianwei Zollo, Thomas P. Bachmat, Eitan Zemel, Richard Deng, Zhun |
| author_facet | Ding, Ruomeng Gao, Tianwei Zollo, Thomas P. Bachmat, Eitan Zemel, Richard Deng, Zhun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_14279 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Whom to Query for What: Adaptive Group Elicitation via Multi-Turn LLM Interactions Ding, Ruomeng Gao, Tianwei Zollo, Thomas P. Bachmat, Eitan Zemel, Richard Deng, Zhun Machine Learning Artificial Intelligence Computation and Language Social and Information Networks 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. |
| title | Whom to Query for What: Adaptive Group Elicitation via Multi-Turn LLM Interactions |
| topic | Machine Learning Artificial Intelligence Computation and Language Social and Information Networks |
| url | https://arxiv.org/abs/2602.14279 |