Thinking Outside the (Gray) Box: A Context-Based Score for Assessing Value and Originality in Neural Text Generation

ICLR 2026 Conference Submission18258 Authors

Keywords: Computational creativity, large language models, reinforcement learning, natural language generation

TL;DR: Drawing on information theory, we propose a context-based score to quantitatively evaluate value and originality that can be used as a reward for tuning language models.

Abstract:

Despite the increasing use of large language models for creative tasks, their outputs often lack diversity. Common solutions, such as sampling at higher temperatures, can compromise the quality of the results. Dealing with this trade-off is still an open challenge in designing AI systems for creativity.
Drawing on information theory, we propose a context-based score to quantitatively evaluate value and originality. This score incentivizes accuracy and adherence to the request while fostering divergence from the learned distribution. We show that our score can be used as a reward in a reinforcement learning framework to fine-tune large language models for maximum performance. We validate our strategy through experiments considering a variety of creative tasks, such as poetry generation and math problem solving, demonstrating that it enhances the value and originality of the generated solutions.

Primary Area: generative models

Submission Number: 18258