{"data":{"id":19,"backendId":"9824a8f9-a11a-4448-a946-8f2f27373f20","title":"Probing Memes in LLMs: A Paradigm for the Entangled Evaluation World","summary":"arXiv:2603.04408v1 Announce Type: new Abstract: Current evaluation paradigms for large language models (LLMs) characterize models and datasets separately, yielding coarse descriptions: items in datasets are treated as pre-labeled entries, and models are summarized by overall scores such as accuracy, together ignoring the diversity of population-level model behaviors across items with varying properties. To address this gap, this paper conceptualizes LLMs as composed of memes, a notion introduced","analysis":"This paper introduces a novel conceptual framework (memes) to solve the 'coarse description' problem in LLM benchmarking, offering a high-scale, paradigm-shifting approach to model assessment.","category":"technology","strategicTrack":"ai_agents","capitalRelevance":{"social":3,"cultural":4,"economic":5,"symbolic":4,"technological":9,"informational":9,"temporal":6,"psychological":1,"physical":0},"tags":["LLM evaluation","memetics","perception matrix","model benchmarking","arXiv"],"qualityScore":10,"valueScore":8,"interestScore":9,"potentialScore":9,"uniquenessScore":9,"sourceCount":1,"confidence":5,"detectedAt":"2026-03-06T06:08:37.512Z","createdAt":"2026-03-06 06:10:03"}}