“‘AI Mode Collapse’ Tag”,2021-10-13 (GPT-4 poetry, GPT calibration, Claude AI, DALL·E 3; backlinks)⁠:

Bibliography for tag reinforcement-learning/preference-learning/mode-collapse, most recent first: 4 related tags, 56 annotations, & 43 links (parent).

[page summary]

• See Also
• Gwern
  • “Commentary on Weaknesses in Midjourney’s New Ranking-Based Personalization Feature”, Gwern2024
  • “Why Do Writers Still Underestimate LLMs?”, Gwern2023
  • “Novelty Nets: Classifier Anti-Guidance”, Gwern2024
• Links
  • “Hidden Persuaders: LLMs’ Political Leaning and Their Influence on Voters”, Potter et al 2024
  • “Do LLMs Estimate Uncertainty Well in Instruction-Following?”, Heo et al 2024
  • “SimpleStrat: Diversifying Language Model Generation With Stratification”, Wong et al 2024
  • “I Quit Teaching Because of ChatGPT”, Livingstone2024
  • “Thoughts While Watching Myself Be Automated”, Dynomight2024
  • “Why AI Isn’t Going to Make Art”, Chiang2024
  • “Epistemic Calibration and Searching the Space of Truth”, Lee2024
  • “Are Large Language Models Consistent over Value-Laden Questions?”, Moore et al 2024
  • “Pron vs Prompt: Can Large Language Models Already Challenge a World-Class Fiction Author at Creative Text Writing?”, Marco et al 2024
  • “Sonnet or Not, Bot? Poetry Evaluation for Large Models and Datasets”, Walsh et al 2024
  • “AI Doesn’t Kill Jobs? Tell That to Freelancers: There’s Now Data to Back up What Freelancers Have Been Saying for Months”, Mims2024
  • “What Are the Odds? Language Models Are Capable of Probabilistic Reasoning”, Paruchuri et al 2024
  • “Consistency-Diversity-Realism Pareto Fronts of Conditional Image Generative Models”, Astolfi et al 2024
  • “Self-Consuming Generative Models With Curated Data Provably Optimize Human Preferences”, Ferbach et al 2024
  • “Creativity Has Left the Chat: The Price of Debiasing Language Models”, Mohammadi2024
  • “I Wish I Knew How to Force Quit You”, Life & Rich2024
  • “Enhancing Confidence Expression in Large Language Models Through Learning from Past Experience”, Han et al 2024
  • “A Tale of Tails: Model Collapse As a Change of Scaling Laws”, Dohmatob et al 2024
  • “The Non-Effect of Sampling Temperature on Problem Solving in GPT-3.5/GPT-4”, Renze & Guven2024
  • “Weaver: Foundation Models for Creative Writing”, Wang et al 2024
  • “Does Using ChatGPT Result in Human Cognitive Augmentation?”, Fulbright & Morrison2024
  • “Originality Dies When Being Average Is Easier”
  • “Experimental Narratives: A Comparison of Human Crowdsourced Storytelling and AI Storytelling”
  • “Helping or Herding? Reward Model Ensembles Mitigate but Do Not Eliminate Reward Hacking”, Eisenstein et al 2023
  • “EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models”, Paech2023
  • “Generative Artificial Intelligence Enhances Creativity but Reduces the Diversity of Novel Content”, Doshi & Hauser2023
  • “When ‘A Helpful Assistant’ Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language Models”, Zheng et al 2023
  • “The Impact of Large Language Models on Scientific Discovery: a Preliminary Study Using GPT-4”, AI4Science & Quantum2023
  • “A Coder Considers the Waning Days of the Craft: Coding Has Always Felt to Me like an Endlessly Deep and Rich Domain. Now I Find Myself Wanting to Write a Eulogy for It”, Somers2023
  • “When Ruthless Cultural Elitism Is Exactly the Job”, Marchese2023
  • “Does GPT-4 Pass the Turing Test?”, Jones & Bergen2023
  • “Large Language Models Can Replicate Cross-Cultural Differences in Personality”, Niszczota et al 2023
  • “Assessing the Nature of Large Language Models: A Caution against Anthropocentrism”, Speed2023
  • “Simple Synthetic Data Reduces Sycophancy in Large Language Models”, Wei et al 2023
  • “I’m a Screenwriter. These AI Jokes Give Me Nightmares”, Rich2023
  • “Can a Chatbot Preach a Good Sermon? Hundreds Attend Church Service Generated by ChatGPT to Find Out”, Grieshaber2023
  • “ChatGPT Is Fun, but It Is Not Funny! Humor Is Still Challenging Large Language Models”, Jentzsch & Kersting2023
  • “The False Promise of Imitating Proprietary LLMs”, Gudibande et al 2023
  • “Bits of Grass: Does GPT Already Know How to Write like Whitman?”, Sawicki et al 2023
  • “Inducing Anxiety in GPT-3.5 Increases Exploration and Bias”, Coda-Forno et al 2023
  • “GPT-4 Technical Report § Limitations: Calibration”, OpenAI 2023 (page 12 org openai)
  • “Rewarding Chatbots for Real-World Engagement With Millions of Users”, Irvine et al 2023
  • “Discovering Language Model Behaviors With Model-Written Evaluations”, Perez et al 2022
  • “Mysteries of Mode Collapse § Inescapable Wedding Parties”, Janus2022
  • “RL With KL Penalties Is Better Viewed As Bayesian Inference”, Korbak et al 2022
  • “Janus”
  • “Situational Awareness and Out-Of-Context Reasoning § GPT-4-Base Has Non-Zero Longform Performance”, Evans2024
  • “I Finally Got ChatGPT to Sound like Me”, lsusr 2024
  • “The Case for More Ambitious Language Model Evals”
  • “GPT-3 Catching Fish in Morse Code”
  • “Mysteries of Mode Collapse”
  • “Mysteries of Mode Collapse”
  • “Please Stop Using Mediocre AI Art in Your Posts”
  • “What Kind of Writer Is ChatGPT?”
  • “The New Poem-Making Machinery”
  • l4rz
  • Sort By Magic
    • cultural-elitism
    • gpt-poetry
    • model-diversity
• Miscellaneous
• Bibliography

Backlinks: