Steering Large Language Models to Evaluate and Amplify Creativity

• URL: http://arxiv.org/abs/2412.06060v1
• Date: Sun, 08 Dec 2024 20:28:48 GMT
• Title: Steering Large Language Models to Evaluate and Amplify Creativity
• Authors: Matthew Lyle Olson, Neale Ratzlaff, Musashi Hinck, Shao-yen Tseng, Vasudev Lal,
• Abstract summary: We show that we can leverage this knowledge of how to write creatively in order to better judge what is creative. We take a mechanistic approach that extracts differences in the internal states of an LLM when prompted to respond "boringly" or "creatively"
• Score: 7.031631627161492
• License:
• Abstract: Although capable of generating creative text, Large Language Models (LLMs) are poor judges of what constitutes "creativity". In this work, we show that we can leverage this knowledge of how to write creatively in order to better judge what is creative. We take a mechanistic approach that extracts differences in the internal states of an LLM when prompted to respond "boringly" or "creatively" to provide a robust measure of creativity that corresponds strongly with human judgment. We also show these internal state differences can be applied to enhance the creativity of generated text at inference time.

Related papers

• A Causality-aware Paradigm for Evaluating Creativity of Multimodal Large Language Models [100.16387798660833]
  Oogiri game is a creativity-driven task requiring humor and associative thinking. LoTbench is an interactive, causality-aware evaluation framework. Results show that while most LLMs exhibit constrained creativity, the performance gap between LLMs and humans is not insurmountable.
  arXiv  Detail & Related papers  (2025-01-25T09:11:15Z)
• A Framework for Collaborating a Large Language Model Tool in Brainstorming for Triggering Creative Thoughts [2.709166684084394]
  This study proposes a framework called GPS, which employs goals, prompts, and strategies to guide designers to systematically work with an LLM tool for improving the creativity of ideas generated during brainstorming. Our framework, tested through a design example and a case study, demonstrates its effectiveness in stimulating creativity and its seamless LLM tool integration into design practices.
  arXiv  Detail & Related papers  (2024-10-10T13:39:27Z)
• AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text [53.15652021126663]
  We present CREATIVITY INDEX as the first step to quantify the linguistic creativity of a text. To compute CREATIVITY INDEX efficiently, we introduce DJ SEARCH, a novel dynamic programming algorithm. Experiments reveal that the CREATIVITY INDEX of professional human authors is on average 66.2% higher than that of LLMs.
  arXiv  Detail & Related papers  (2024-10-05T18:55:01Z)
• Creativity Has Left the Chat: The Price of Debiasing Language Models [1.223779595809275]
  We investigate the unintended consequences of Reinforcement Learning from Human Feedback on the creativity of Large Language Models (LLMs) Our findings have significant implications for marketers who rely on LLMs for creative tasks such as copywriting, ad creation, and customer persona generation.
  arXiv  Detail & Related papers  (2024-06-08T22:14:51Z)
• Divergent Creativity in Humans and Large Language Models [37.67363469600804]
  The recent surge in the capabilities of Large Language Models has led to claims that they are approaching a level of creativity akin to human capabilities. We leverage recent advances in creativity science to build a framework for in-depth analysis of divergent creativity in both state-of-the-art LLMs and a substantial dataset of 100,000 humans.
  arXiv  Detail & Related papers  (2024-05-13T22:37:52Z)
• 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)
• Art or Artifice? Large Language Models and the False Promise of Creativity [53.04834589006685]
  We propose the Torrance Test of Creative Writing (TTCW) to evaluate creativity as a product. TTCW consists of 14 binary tests organized into the original dimensions of Fluency, Flexibility, Originality, and Elaboration. Our analysis shows that LLM-generated stories pass 3-10X less TTCW tests than stories written by professionals.
  arXiv  Detail & Related papers  (2023-09-25T22:02:46Z)
• Putting GPT-3's Creativity to the (Alternative Uses) Test [0.0]
  We put Open AI's generative natural language model, GPT-3, to the test. We assessed GPT-3's creativity on Guilford's Alternative Uses Test. Humans currently outperform GPT-3 when it comes to creative output.
  arXiv  Detail & Related papers  (2022-06-10T15:36:45Z)
• DeepCreativity: Measuring Creativity with Deep Learning Techniques [2.5426469613007012]
  This paper explores the possibility of using generative learning techniques for automatic assessment of creativity. We introduce a new measure, namely DeepCreativity, based on Margaret Boden's definition of creativity as composed by value, novelty and surprise.
  arXiv  Detail & Related papers  (2022-01-16T19:00:01Z)
• Telling Creative Stories Using Generative Visual Aids [52.623545341588304]
  We asked writers to write creative stories from a starting prompt, and provided them with visuals created by generative AI models from the same prompt. Compared to a control group, writers who used the visuals as story writing aid wrote significantly more creative, original, complete and visualizable stories. Findings indicate that cross modality inputs by AI can benefit divergent aspects of creativity in human-AI co-creation, but hinders convergent thinking.
  arXiv  Detail & Related papers  (2021-10-27T23:13:47Z)
• Explaining Creative Artifacts [69.86890599471202]
  We develop an inverse problem formulation to deconstruct the products of and compositional creativity into associative chains. In particular, our formulation is structured as solving a traveling salesman problem through a knowledge graph of associative elements.
  arXiv  Detail & Related papers  (2020-10-14T14:32:38Z)

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.