Skip to content
Book Open access

Curiosity-Driven Questioning for Engine-Agnostic LLM Research Ideation

Aug 2026 · Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 · pp. 11016-11027 · 0 citations · 44 references

Abstract

Scientific ideation is driven by curiosity: researchers ask questions that expose knowledge gaps, reveal competing hypotheses, and clarify missing evidence relevant to decision making. Yet, most LLM-based ideation systems optimize the idea text while leaving curiosity under-modeled, resulting in brittle, engine-specific gains. To address this, we propose Curiosity-Driven Questioning (CDQ), a training-free, engine-agnostic method that constructs a compact set of curiosity-driven questions from a topic corpus under black-box LLM access. CDQ scores questions with three corpus-relative indices (GapExposure, DisagrDiversity, ClarityGain) and uses a two-stage scoring with an entropic mirror-ascent reweighting over question meta-policies to concentrate on high-utility question policies. Our results show that prepending CDQ questions improves downstream ideation across single-pass, retrieval-augmented generation, and self-reflection engines with multiple base models under preference-based evaluation. Ablations and a human study further support the complementarity of the indices and the reliability of the evaluation. Our code and dataset are available at: https://github.com/Sikun-Skyler-Guo/CDQ

Read PDF

Similar papers

#artificial intelligence Preprint Oct 2026

Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering

Large language models (LLMs) have demonstrated strong capabilities in question answering, yet they still frequently suffer from hallucinations on knowledge-intensive tasks. Knowledge graphs (KGs) provide LLMs with structured, interpretable, and updatable factual grounding, making them a promising external knowledge sou...

Yang Hong, Ya-Jun Yang, Xin Wang et al. · 0 citations

LLMs as Feature Engineers for Text-and-Tabular Prediction

An iterative framework that automates the extraction of interpretable, schema-bound categorical features from unstructured text for tabular prediction models that guarantees instance-level interpretability and provides a fully transparent, semantic audit trail for every prediction.

Merwan Barlier, Blaž Škrlj · 1 citation
#machine learning Preprint Sep 2026

Beyond Scores: Understanding LLM-as-a-Judge Mechanisms in Summarization Evaluation

This work investigates LLM-based evaluators of natural language generation quality mechanistically through an eight-attack perturbation taxonomy across the Readability and Adequacy dimensions of NLG quality, a generation pipeline that produces paired clean and corrupt summaries with controlled error intensity and expli...

Himil Vasava, Ming-Zhou Jiang · 0 citations
#natural language process... Conference Open access Sep 2026

Grounding Memory Summarization in Utility Intent

This work proposes MemSuit, a self-distillation framework in which a teacher summarizer, conditioned on observed query-answer pairs, produces utility-aware memory entries that a student learns to reproduce from the raw conversation alone, confirming the value of grounding memory in downstream utility.

Zhen-Yu Lei, Ming-Jia Shi, Xing-Bo Fu et al. · 0 citations
Book Open access Sep 2026

Seek: Self-Evaluative Exploration for Knowledge Retrieval

seek, Self-Evaluative Exploration for Knowledge Retrieval, a training-free framework that addresses this limitation through iterative corpus interaction at test time through iterative corpus interaction at test time.

Amin Bigdeli, Radin Hamidi Rad, Negar Arabzadeh et al. · 1 citation
Open access Oct 2026

The Grounding Tax: How Domain Fine-Tuning Suppresses Context Utilisation in Retrieval-Augmented Generation

Large language models (LLMs) are routinely adapted to specialised domains through fine-tuning and grounded in external evidence through retrieval-augmented generation (RAG). The prevailing assumption is that these methods are complementary even though minimal empirical work examines whether domain-specific fine-tuning...

Usman Yunusa Labaran, Rufai Yauri Aliyu, C. I. Saidu et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.