PulseAugur
LIVE 06:33:20
research · [2 sources] ·
0
research

Paper challenges cosine similarity metric for neural representations

A new paper published on arXiv argues that mean-pooled cosine similarity, a common metric for comparing neural representations, is not length-invariant. The researchers demonstrate that sequence length alone can heavily influence this metric, potentially skewing results in cross-lingual and cross-modal comparisons. They propose using Centered Kernel Alignment (CKA) as a more robust, length-invariant alternative for evaluating representational similarity. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Challenges the validity of common evaluation metrics, potentially impacting how model performance is assessed and compared.

RANK_REASON Academic paper proposing a new methodology for evaluating neural representations.

Read on arXiv cs.CL →

COVERAGE [2]

  1. arXiv cs.CL TIER_1 · Dhruv Kumar ·

    Mean-Pooled Cosine Similarity is Not Length-Invariant: Theory and Cross-Domain Evidence for a Length-Invariant Alternative

    Mean-pooled cosine similarity is the default metric for comparing neural representations across languages, modalities, and tasks. We establish that this metric is not length-invariant: under the anisotropy that characterizes modern transformer representations, mean-pooled cosine …

  2. Medium — MCP tag TIER_1 · WebWizardsSG ·

    How RAG Uses Cosine Similarity — And Why It Matters

    <div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@yanguangchensp/how-rag-uses-cosine-similarity-and-why-it-matters-87e97987f6b5?source=rss------mcp-5"><img src="https://cdn-images-1.medium.com/max/1600/0*S1lv5Y7ZjTqBpot4.jpg" width="1600" /><…