mlsanityData to 14 Oct 2026

MONAL: Model Autophagy Analysis for Modeling Human-AI Interactions

arXiv 2402.11271 ↗First posted 17 Feb 2024cs.CL cs.CY cs.HCcited by 7

Not on the map. Why?

Abstract (arXiv)

The increasing significance of large models and their multi-modal variants in societal information processing has ignited debates on social safety and ethics. However, there exists a paucity of comprehensive analysis for: (i) the interactions between human and artificial intelligence systems, and (ii) understanding and addressing the associated limitations. To bridge this gap, we propose Model Autophagy Analysis (MONAL) for large models' self-consumption explanation. MONAL employs two distinct autophagous loops (referred to as ``self-consumption loops'') to elucidate the suppression of human-generated information in the exchange between human and AI systems. Through comprehensive experiments on diverse datasets, we evaluate the capacities of generated models as both creators and disseminators of information. Our key findings reveal (i) A progressive prevalence of model-generated synthetic information over time within training datasets compared to human-generated information; (ii) The discernible tendency of large models, when acting as information transmitters across multiple iterations, to selectively modify or prioritize specific contents; and (iii) The potential for a reduction in the diversity of socially or human-generated information, leading to bottlenecks in the performance enhancement of large models and confining them to local optima.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 26 of its 58 references that are in the map. First posted on arXiv 17 Feb 2024.

Builds on

26 of 58 references.

References · 26

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  2. 2023Qwen Technical Reportcited by 3,344
  3. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  4. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,411
  5. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  6. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,031
  7. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  8. 2023A Survey on Multimodal Large Language Modelscited by 909
  9. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 843
  10. 2023The Curse of Recursion: Training on Generated Data Makes Models Forgetcited by 356
  11. 2023S3: Social-network Simulation System with Large Language Model-Empowered Agentscited by 233
  12. 2023An LLM can Fool Itself: A Prompt-Based Adversarial Attackcited by 116
14 more
  1. 2023Artificial Artificial Artificial Intelligence: Crowd Workers Widely Use Large Language Models for Text Production Taskscited by 103
  2. 2023LLMs as Narcissistic Evaluators: When Ego Inflates Evaluation Scorescited by 90
  3. 2023Large Language Models Suffer From Their Own Output: An Analysis of the Self-Consuming Training Loopcited by 79
  4. 2023Style Over Substance: Evaluation Biases for Large Language Modelscited by 70
  5. 2021High Dimensional Differentially Private Stochastic Optimization with Heavy-tailed Datacited by 42
  6. 2022SEAT: Stable and Explainable Attentioncited by 25
  7. 2023Differentially Private Natural Language Models: Recent Advances and Future Directionscited by 20
  8. 2023Practical Differentially Private and Byzantine-resilient Federated Learningcited by 18
  9. 2023Influence of External Information on Large Language Models Mirrors Social Cognitive Patternscited by 16
  10. 2020Fine-Grained Named Entity Typing over Distantly Supervised Data Based on Refined Representationscited by 12
  11. 2021Faster Rates of Private Stochastic Convex Optimizationcited by 12
  12. 2023Differentially Private Non-convex Learning for Multi-layer Neural Networkscited by 10
  13. 2019Estimating Smooth GLM in Non-interactive Local Differential Privacy Model with Public Unlabeled Datacited by 9
  14. 2022GPT-D: Inducing Dementia-related Linguistic Anomalies by Deliberate Degradation of Artificial Neural Language Modelscited by 8

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 5.

7 papers.

  1. 2024Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracycited by 67
  2. 2025Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducementscited by 32
  3. 2024A Hopfieldian View-based Interpretation for Chain-of-Thought Reasoningcited by 15
  4. 2025Delving into: the quantification of Ai-generated content on the internet (synthetic data)cited by 10
  5. 2025Rethinking Prompt-based Debiasing in Large Language Modelscited by 4
  6. 2025Information Retrieval in the Age of Generative AI: The RGB Modelcited by 2
  7. 2025Mitigating Behavioral Hallucination in Multimodal Large Language Models for Sequential Imagescited by 1