IntElicit: Eliciting and Assessing Contextualized Creativity via Dialogue Policy Optimization

• URL: http://arxiv.org/abs/2606.12086v1
• Date: Wed, 10 Jun 2026 13:47:54 GMT
• Title: IntElicit: Eliciting and Assessing Contextualized Creativity via Dialogue Policy Optimization
• Abstract summary: IntElicit is a framework for eliciting and assessing contextualized creativity via dialogue policy optimization.<n>It provides non-directive knowledge and agency scaffolds in multi-turn interaction to reduce non-creative confounders.<n>Experiments show that IntElicit improves elicited creative outcomes over expert-designed baselines.
• Score: 37.83315648613522
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• DEFINED: A Data-Efficient Computational Framework for Fine-Grained Creativity Assessment in Debate Scenarios [25.233538120209857]
  DEFINED is a data-efficient framework for fine-grained creativity assessment in debate scenarios.<n> DEFINED operationalizes debate creativity through a hierarchical eight-dimensional metric system.<n>Our scoring model achieves accurate and stable scoring, outperforming prompt-based large language model evaluators.
  arXiv  Detail & Related papers  (2026-06-05T12:42:56Z)
• Measuring Creativity in the Age of Generative AI: Distinguishing Human and AI-Generated Creative Performance in Hiring and Talent Systems [0.0]
  This paper reconceptualizes creativity as a distributional and process-based property that emerges under shared constraints and competitive incentives.<n>We introduce a quantitative framework for measuring creativity as novelty in synthesis, operationalized through idea generation and idea transformation within embedding space.<n>The findings suggest that in the age of generative AI, distinctiveness rather than fluency becomes the primary signal of human creative capability.
  arXiv  Detail & Related papers  (2026-04-10T12:49:17Z)
• The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning [76.96796481909581]
  Internal cognitive processing is instrumental in formulating high-quality responses.<n>We propose a novel method named FLAIR that conducts latent thinking simultaneously with speech perception.<n>Our approach aligns seamlessly with spoken dialogue systems.
  arXiv  Detail & Related papers  (2026-03-18T15:30:29Z)
• Enhancing AI-Driven Education: Integrating Cognitive Frameworks, Linguistic Feedback Analysis, and Ethical Considerations for Improved Content Generation [0.0]
  This paper synthesizes insights from four related studies to propose a comprehensive framework for enhancing AI-driven educational tools.<n>We integrate cognitive assessment frameworks, linguistic analysis of AI-generated feedback, and ethical design principles to guide the development of effective and responsible AI tools.
  arXiv  Detail & Related papers  (2025-05-01T06:36:21Z)
• Beyond Detection: Designing AI-Resilient Assessments with Automated Feedback Tool to Foster Critical Thinking [0.0]
  This research proposes a proactive, AI-resilient solution based on assessment design rather than detection.<n>It introduces a web-based Python tool that integrates Bloom's taxonomy with advanced natural language processing techniques.<n>It helps educators determine whether a task targets lower-order thinking such as recall and summarization or higher-order skills such as analysis, evaluation, and creation.
  arXiv  Detail & Related papers  (2025-03-30T23:13:00Z)
• Can AI Be as Creative as Humans? [84.43873277557852]
  We prove in theory that AI can be as creative as humans under the condition that it can properly fit the data generated by human creators. The debate on AI's creativity is reduced into the question of its ability to fit a sufficient amount of data.
  arXiv  Detail & Related papers  (2024-01-03T08:49:12Z)
• Interactive Natural Language Processing [67.87925315773924]
  Interactive Natural Language Processing (iNLP) has emerged as a novel paradigm within the field of NLP. This paper offers a comprehensive survey of iNLP, starting by proposing a unified definition and framework of the concept.
  arXiv  Detail & Related papers  (2023-05-22T17:18:29Z)
• CHAI-DT: A Framework for Prompting Conversational Generative AI Agents to Actively Participate in Co-Creation [0.0]
  This paper explores the potential for utilizing generative AI models in group-focused co-creative frameworks to enhance problem solving and ideation. We propose a novel prompting technique for conversational generative AI agents which employ methods inspired by traditional 'human-to-human' facilitation and instruction.
  arXiv  Detail & Related papers  (2023-05-05T21:25:35Z)
• Interacting with Non-Cooperative User: A New Paradigm for Proactive Dialogue Policy [83.61404191470126]
  We propose a new solution named I-Pro that can learn Proactive policy in the Interactive setting. Specifically, we learn the trade-off via a learned goal weight, which consists of four factors. The experimental results demonstrate I-Pro significantly outperforms baselines in terms of effectiveness and interpretability.
  arXiv  Detail & Related papers  (2022-04-07T14:11:31Z)
• You Impress Me: Dialogue Generation via Mutual Persona Perception [62.89449096369027]
  The research in cognitive science suggests that understanding is an essential signal for a high-quality chit-chat conversation. Motivated by this, we propose P2 Bot, a transmitter-receiver based framework with the aim of explicitly modeling understanding.
  arXiv  Detail & Related papers  (2020-04-11T12:51:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.