DeepCreativity: measuring creativity with deep learning techniques

Giorgio, Franceschelli,; Musolesi, Mirco

doi:10.3233/ia-220136

Cited by 8 publications

(9 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This methodology has already shown its intrinsic value in obtaining accurate, helpful, and useful text. In the same way, these techniques can be applied to other domains in which desired qualities are difficult to quantify or hard to express in a mathematical form, e.g., aesthetically pleasant or personalized (multimodal) content or creative artifacts (Franceschelli & Musolesi, 2023). A summary on the applications discussed in this paper is reported in Table 2.…”

Section: Discussionmentioning

confidence: 99%

Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges

Franceschelli,

Musolesi

2024

jair

View full text Add to dashboard Cite

Generative Artificial Intelligence (AI) is one of the most exciting developments in Computer Science of the last decade. At the same time, Reinforcement Learning (RL) has emerged as a very successful paradigm for a variety of machine learning tasks. In this survey, we discuss the state of the art, opportunities and open research questions in applying RL to generative AI. In particular, we will discuss three types of applications, namely, RL as an alternative way for generation without specified objectives; as a way for generating outputs while concurrently maximizing an objective function; and, finally, as a way of embedding desired characteristics, which cannot be easily captured by means of an objective function, into the generative process. We conclude the survey with an in-depth discussion of the opportunities and challenges in this fascinating emerging area.

show abstract

Section: Discussionmentioning

confidence: 99%

Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges

Franceschelli,

Musolesi

2024

jair

View full text Add to dashboard Cite

show abstract

“…However, in this case, the "creativity" of the task was somewhat diminished by having prescribed rules about the topic, characters, and writing style, where the task may be more construed as emulating the writing of an existing work. However, similarly, both Clark et al (2021) and Franceschelli and Musolesi (2023) observe that humans are infrequently able to distinguish creative works written by other humans from those authored by LLMs, with the latter often achieving very high-quality outputs. Overall, there is clear potential and room for improvement in the field of automatically generating creative language forms.…”

Section: Creative Language Generationmentioning

confidence: 96%

TwistList: Resources and Baselines for Tongue Twister Generation

Tyler¹,

Tang²,

Lin³

2023

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

View full text Add to dashboard Cite

Previous work in phonologically and phonetically grounded language generation has mainly focused on domains such as puns and poetry. In this article, we present new work on the generation of tongue-twisters -a form of language that is required to be conditioned on a phoneme level to maximize sound overlap, whilst maintaining semantic consistency with an input topic and still being grammatically correct. We present TwisterLister, a pipeline for generating phonologically informed tongue-twisters from Large Language Models (LLMs) that we use to generate TwistList 2.0, the largest annotated dataset of tongue-twisters to date, consisting of 17K+ examples from a combination of human and LLM authors. Our generation pipeline involves the use of a phonologically constrained vocabulary alongside LLM prompting to generate novel, nonderivative tongue-twister examples. We additionally present the results of automatic and human evaluation of smaller models trained on our generated dataset to demonstrate the extent to which phonologically motivated language types can be generated without explicit injection of phonological knowledge. Additionally, we introduce a Phoneme-Aware Constrained Decoding module (PACD) that can be integrated into any causal language model and demonstrate that this method generates good quality tongue-twisters both with and without fine-tuning the underlying language model. We also design and implement a range of automatic metrics for the task of tongue-twister generation that is phonologically motivated and captures the unique essence of tongue-twisters based on Phonemic Edit Distance (PED).

show abstract

“…Recently, Lehman et al [87] gave an extensive account of cases where artificial life simulations exhibited completely unexpected behaviours. Extensive work has done on using deep learning for creativity [54].…”

Section: Novelty Innovation and Creativitymentioning

confidence: 99%

Open-endedness in synthetic biology: a route to continual innovation for biological design

Stock¹,

Gorochowski²

2023

Preprint

View full text Add to dashboard Cite

Design in synthetic biology is typically goal-oriented: aiming to repurpose and optimize existing biological functions for new contexts, augmenting biology with new-to-nature capabilities, or creating life-like systems from scratch. While the field has seen many advances over the past two decades, bottlenecks in the complexity of the systems built are emerging and designs that function in the lab often fail when used in real-world contexts. Here, we propose an open-ended approach to biological design that aims to continuously generate innovative solutions capable of overcoming such hurdles. The fundamental principle we put forward is that the novelty of designed biology, be it a protein, genetic construct or organism, is at least as important as how well it fulfils its goal. Designing with novelty in mind, rather than a sole focus on optimization towards a single ``best'' design, may allow us to move beyond the diminishing returns we see in performance for most engineered biology to date. Research from the artificial life and evolutionary computing communities has demonstrated that embracing novelty can allow for the automatic generation of innovative and surprising solutions to challenging problems that move us beyond local optima. Synthetic biology now offers the ideal playground to test these ideas in living systems and explore more creative approaches to biological design.

show abstract

DeepCreativity: measuring creativity with deep learning techniques

Cited by 8 publications

References 21 publications

Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges

Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges

TwistList: Resources and Baselines for Tongue Twister Generation

Open-endedness in synthetic biology: a route to continual innovation for biological design

Contact Info

Product

Resources

About