[Paper] IntElicit: Eliciting and Assessing Contextualized Creativity via Dialogue Policy Optimization
Source: arXiv - 2606.12086v1
Overview
Contextualized assessment offers high ecological validity for evaluating creativity but introduces a critical challenge: observed performance may be confounded with cognitive proficiency (domain knowledge) and agency (willingness to engage). Meanwhile, in the age of generative AI, creative problem solving increasingly occurs in tool-mediated and human—AI interactive environments, making fully static assessment less aligned with contemporary creative practice. To address these issues, this paper proposes IntElicit, a framework for eliciting and assessing contextualized creativity via dialogue policy optimization. IntElicit functions as a constrained adaptive AI Interviewer: it provides non-directive knowledge and agency scaffolds in multi-turn interaction to reduce non-creative confounders, while preserving participants’ responsibility for generating the creative content being evaluated. Specifically, to tackle sparse rewards and potential reward hacking (e.g., answer dictation) in open-ended educational dialogue, IntElicit introduces a decomposed process reward mechanism. This mechanism aligns the policy with pedagogical elicitation, rewarding prompts that draw out participant reasoning rather than producing optimal answers on their behalf. Extensive experiments, including participant simulation and a human subject study (N=64), show that IntElicit improves elicited creative outcomes over expert-designed baselines. Together, the results suggest that interactive elicitation can reveal creative potential that static FPSP-style assessment may miss, providing a formative and diagnostic lens for contextualized creativity assessment in AI-mediated learning contexts.
Key Contributions
This paper presents research in the following areas:
- cs.AI
- cs.LG
Methodology
Please refer to the full paper for detailed methodology.
Practical Implications
This research contributes to the advancement of cs.AI.
Authors
- Mingjia Li
- Jin Wu
- Hong Qian
- Wenhao Huang
- Yiyang Huang
- Yiwen Zhang
- Chanjin Zheng
- Xiangfeng Wang
- Aimin Zhou
- Jiajun Guo
Paper Information
- arXiv ID: 2606.12086v1
- Categories: cs.AI, cs.LG
- Published: June 10, 2026
- PDF: Download PDF