paper-with-me

홈 › Papers

RPS: Information Elicitation with Reinforcement Prompt Selection

2026-04-15 · Tao Wang, Jingyao Lu, Xibo Wang, Haonan Huang, Su Yao, Zhiqiang Hu, Xingyan Chen, Enmao Diao arxiv

Large language models (LLMs) have shown remarkable capabilities in dialogue generation and reasoning, yet their effectiveness in eliciting user-known but concealed information in open-ended conversations remains limited. In many interactive AI applications, such as personal assistants, tutoring systems, and legal or clinical support, users often withhold sensitive or uncertain information due to privacy concerns, ambiguity, or social hesitation. This makes it challenging for LLMs to gather complete and contextually relevant inputs. In this work, we define the problem of information elicitation in open-ended dialogue settings and propose Reinforcement Prompt Selection (RPS), a lightweight reinforcement learning framework that formulates prompt selection as a sequential decision-making problem. To analyze this problem in a controlled setting, we design a synthetic experiment, where a reinforcement learning agent outperforms a random query baseline, illustrating the potential of policy-based approaches for adaptive information elicitation. Building on this insight, RPS learns a policy over a pool of prompts to adaptively elicit concealed or incompletely expressed information from users through dialogue. We also introduce IELegal, a new benchmark dataset constructed from real legal case documents, which simulates dialogue-based information elicitation tasks aimed at uncovering case-relevant facts. In this setting, RPS outperforms static prompt baselines, demonstrating the effectiveness of adaptive prompt selection for eliciting critical information in LLM-driven dialogue systems.

📄 PDF Abstract BibTeX arXiv:2604.13817

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningDialogue Generation

Similar Papers 제목 키워드 기반

Personalized Algorithmic Recourse with Preference Elicitation

2022-05-27 · Giovanni De Toni, Paolo Viappiani, Stefano Teso, Bruno Lepri 외

Algorithmic Recourse (AR) is the problem of computing a sequence of actions that -- once performed by a user -- overturns an undesirable machine decision. It is paramount that the sequence of actions does not require too…

Efficient Exploration

A First Look at Selection Bias in Preference Elicitation for Recommendation

2024-05-01 · Shashank Gupta, Harrie Oosterhuis, Maarten de Rijke

Preference elicitation explicitly asks users what kind of recommendations they would like to receive. It is a popular technique for conversational recommender systems to deal with cold-starts. Previous work has studied s…

Recommendation SystemsSelection bias

Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation

2026-03-05 · Helena Casademunt, Bartosz Cywiński, Khoi Tran, Arya Jakkli 외 arxiv

Large language models sometimes produce false or misleading responses. Two approaches to this problem are honesty elicitation -- modifying prompts or weights so that the model answers truthfully -- and lie detection -- c…

Eliciting Harmful Capabilities by Fine-Tuning On Safeguarded Outputs

2026-01-20 · Jackson Kaunismaa, Avery Griffin, John Hughes, Christina Q. Knight 외 arxiv

Model developers implement safeguards in frontier models to prevent misuse, for example, by employing classifiers to filter dangerous outputs. In this work, we demonstrate that even robustly safeguarded models can be use…

Combining Confidence Elicitation and Sample-based Methods for Uncertainty Quantification in Misinformation Mitigation

2024-01-13 · Mauricio Rivera, Jean-François Godbout, Reihaneh Rabbany, Kellin Pelrine

Large Language Models have emerged as prime candidates to tackle misinformation mitigation. However, existing approaches struggle with hallucinations and overconfident predictions. We propose an uncertainty quantificatio…

MisinformationUncertainty Quantification