PulseAugur
EN
LIVE 22:06:06

Model collapse explained by cultural evolution theory

Researchers have reframed the phenomenon of model collapse, where large language models degrade when trained on their own outputs, as a cultural evolution process. By applying iterated learning theory, they derived and tested five predictions using LLaMA-2-7B and Mistral-7B models across multiple languages. A key finding was that compositionality initially increases then decreases during unfiltered self-training, a pattern that persists even with regularized data and is only mitigated by task-grounded filtering. AI

IMPACT Offers a new theoretical lens for understanding and mitigating model collapse, potentially improving self-training pipeline design.

RANK_REASON The cluster contains an academic paper detailing a new theoretical framework and experimental validation for a known AI phenomenon.

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

COVERAGE [2]

  1. arXiv cs.AI TIER_1 Italiano(IT) · Dongxin Guo, Jikun Wu, Siu Ming Yiu ·

    Model Collapse as Cultural Evolution

    arXiv:2605.23054v1 Announce Type: cross Abstract: Model collapse, the progressive degradation of LLMs trained on their own outputs, has been characterized statistically but lacks a linguistic explanation for which structures degrade, in what order, and why. We show that iterated …

  2. arXiv cs.CL TIER_1 Italiano(IT) · Siu Ming Yiu ·

    Model Collapse as Cultural Evolution

    Model collapse, the progressive degradation of LLMs trained on their own outputs, has been characterized statistically but lacks a linguistic explanation for which structures degrade, in what order, and why. We show that iterated learning theory from cultural evolution fills this…