Difference between revisions of "AI creativity"
KevinYager (talk | contribs) (→Research) |
KevinYager (talk | contribs) (→Collapse) |
||
| (9 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
=Research= | =Research= | ||
| + | * 2024-01: [https://arxiv.org/abs/2402.01727 Prompting Diverse Ideas: Increasing AI Idea Variance] | ||
| + | * 2024-01: [https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4686415 Creativity and AI] | ||
* 2024-09: [https://arxiv.org/abs/2409.04109 Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers] | * 2024-09: [https://arxiv.org/abs/2409.04109 Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers] | ||
* 2024-11: <strike>[https://aidantr.github.io/files/AI_innovation.pdf Artificial Intelligence, Scientific Discovery, and Product Innovation]</strike> | * 2024-11: <strike>[https://aidantr.github.io/files/AI_innovation.pdf Artificial Intelligence, Scientific Discovery, and Product Innovation]</strike> | ||
| Line 6: | Line 8: | ||
* 2024-12: [https://arxiv.org/abs/2412.14141 LLMs can realize combinatorial creativity: generating creative ideas via LLMs for scientific research] | * 2024-12: [https://arxiv.org/abs/2412.14141 LLMs can realize combinatorial creativity: generating creative ideas via LLMs for scientific research] | ||
* 2024-12: [https://arxiv.org/abs/2412.17596 LiveIdeaBench: Evaluating LLMs' Scientific Creativity and Idea Generation with Minimal Context] | * 2024-12: [https://arxiv.org/abs/2412.17596 LiveIdeaBench: Evaluating LLMs' Scientific Creativity and Idea Generation with Minimal Context] | ||
| + | * 2025-03: [https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5188231 The Cybernetic Teammate: A Field Experiment on Generative AI Reshaping Teamwork and Expertise] | ||
* 2025-03: Midjourney: [https://www.arxiv.org/abs/2503.17126 Modifying Large Language Model Post-Training for Diverse Creative Writing] | * 2025-03: Midjourney: [https://www.arxiv.org/abs/2503.17126 Modifying Large Language Model Post-Training for Diverse Creative Writing] | ||
* 2025-04: [https://arxiv.org/abs/2504.12320 Has the Creativity of Large-Language Models peaked? An analysis of inter- and intra-LLM variability] | * 2025-04: [https://arxiv.org/abs/2504.12320 Has the Creativity of Large-Language Models peaked? An analysis of inter- and intra-LLM variability] | ||
* 2025-05: [https://arxiv.org/abs/2505.14442 Creative Preference Optimization] | * 2025-05: [https://arxiv.org/abs/2505.14442 Creative Preference Optimization] | ||
* 2025-05: [https://arxiv.org/abs/2505.17241 Generative AI and Creativity: A Systematic Literature Review and Meta-Analysis] | * 2025-05: [https://arxiv.org/abs/2505.17241 Generative AI and Creativity: A Systematic Literature Review and Meta-Analysis] | ||
| + | * 2025-10: [https://arxiv.org/abs/2510.01171 Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity] | ||
| + | * 2025-10: [https://arxiv.org/abs/2510.20635 Why Did Apple Fall To The Ground: Evaluating Curiosity In Large Language Model] | ||
| + | * 2025-10: [https://arxiv.org/abs/2510.22954 Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)] | ||
| + | * 2025-12: [https://www.nature.com/articles/s41562-025-02331-1 A large-scale comparison of divergent creativity in humans and large language models] | ||
| + | * 2026-01: [https://www.arxiv.org/abs/2601.01576 OpenNovelty: An LLM-powered Agentic System for Verifiable Scholarly Novelty Assessment] | ||
| + | * 2026-01: [https://www.nature.com/articles/s41598-025-25157-3 Divergent creativity in humans and large language models] | ||
=Benchmarks= | =Benchmarks= | ||
See: [[AI_benchmarks#Creativity| AI benchmarks > Creativity]] | See: [[AI_benchmarks#Creativity| AI benchmarks > Creativity]] | ||
| + | |||
| + | =Collapse= | ||
| + | * 2024-07: [https://www.nature.com/articles/s41586-024-07566-y AI models collapse when trained on recursively generated data] | ||
| + | * 2024-07: [https://arxiv.org/abs/2407.02209 Generative Monoculture in Large Language Models] | ||
| + | * 2024-12: [https://arxiv.org/abs/2412.17646 Rate of Model Collapse in Recursive Training] | ||
| + | ==Analysis== | ||
| + | * 2024-02: [https://arxiv.org/abs/2402.04376 Scaling laws for learning with real and surrogate data] | ||
| + | * 2024-02: [https://arxiv.org/abs/2402.07712 Model Collapse Demystified: The Case of Regression] | ||
| + | ==LLM== | ||
| + | * 2023-05: [https://arxiv.org/abs/2305.17493 The Curse of Recursion: Training on Generated Data Makes Models Forget] | ||
| + | * 2024-04: [https://arxiv.org/abs/2404.03502 AI and the Problem of Knowledge Collapse] | ||
| + | * 2025-10: [https://arxiv.org/abs/2510.13928 LLMs Can Get "Brain Rot"!] | ||
| + | ==Image Models== | ||
| + | * 2023-07: [https://arxiv.org/abs/2307.01850 Self-Consuming Generative Models Go MAD] | ||
| + | * 2023-10: [https://arxiv.org/abs/2310.00429 On the Stability of Iterative Retraining of Generative Models on their own Data] | ||
| + | ==Solutions== | ||
| + | * 2024-03: [https://arxiv.org/abs/2403.04706 Common 7B Language Models Already Possess Strong Math Capabilities] | ||
| + | * 2024-04: [https://arxiv.org/abs/2404.01413 Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data] | ||
| + | * 2024-06: [https://arxiv.org/abs/2406.07515 Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification] | ||
| + | * 2024-07: [https://arxiv.org/abs/2407.01490 LLM See, LLM Do: Guiding Data Generation to Target Non-Differentiable Objectives] | ||
| + | * 2024-08: [https://arxiv.org/abs/2408.14960 Multilingual Arbitrage: Optimizing Data Pools to Accelerate Multilingual Progress] | ||
=See Also= | =See Also= | ||
Latest revision as of 08:56, 4 February 2026
Contents
Research
- 2024-01: Prompting Diverse Ideas: Increasing AI Idea Variance
- 2024-01: Creativity and AI
- 2024-09: Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers
- 2024-11:
Artificial Intelligence, Scientific Discovery, and Product Innovation- 2025-05: Retraction: Assuring an accurate research record
- 2024-12: Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models
- 2024-12: LLMs can realize combinatorial creativity: generating creative ideas via LLMs for scientific research
- 2024-12: LiveIdeaBench: Evaluating LLMs' Scientific Creativity and Idea Generation with Minimal Context
- 2025-03: The Cybernetic Teammate: A Field Experiment on Generative AI Reshaping Teamwork and Expertise
- 2025-03: Midjourney: Modifying Large Language Model Post-Training for Diverse Creative Writing
- 2025-04: Has the Creativity of Large-Language Models peaked? An analysis of inter- and intra-LLM variability
- 2025-05: Creative Preference Optimization
- 2025-05: Generative AI and Creativity: A Systematic Literature Review and Meta-Analysis
- 2025-10: Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity
- 2025-10: Why Did Apple Fall To The Ground: Evaluating Curiosity In Large Language Model
- 2025-10: Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
- 2025-12: A large-scale comparison of divergent creativity in humans and large language models
- 2026-01: OpenNovelty: An LLM-powered Agentic System for Verifiable Scholarly Novelty Assessment
- 2026-01: Divergent creativity in humans and large language models
Benchmarks
See: AI benchmarks > Creativity
Collapse
- 2024-07: AI models collapse when trained on recursively generated data
- 2024-07: Generative Monoculture in Large Language Models
- 2024-12: Rate of Model Collapse in Recursive Training
Analysis
- 2024-02: Scaling laws for learning with real and surrogate data
- 2024-02: Model Collapse Demystified: The Case of Regression
LLM
- 2023-05: The Curse of Recursion: Training on Generated Data Makes Models Forget
- 2024-04: AI and the Problem of Knowledge Collapse
- 2025-10: LLMs Can Get "Brain Rot"!
Image Models
- 2023-07: Self-Consuming Generative Models Go MAD
- 2023-10: On the Stability of Iterative Retraining of Generative Models on their own Data
Solutions
- 2024-03: Common 7B Language Models Already Possess Strong Math Capabilities
- 2024-04: Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data
- 2024-06: Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification
- 2024-07: LLM See, LLM Do: Guiding Data Generation to Target Non-Differentiable Objectives
- 2024-08: Multilingual Arbitrage: Optimizing Data Pools to Accelerate Multilingual Progress
