AI RESEARCH
The Harder Text Embedding Benchmark (HTEB): Beyond One-dimensional Static Robustness
arXiv CS.CL
•
ArXi:2605.28190v1 Announce Type: new Embedding benchmarks like MTEB report a single score per model, implicitly treating robustness as a static, scalar property. We argue that embedding robustness is multidimensional, since models respond differently to different types of variation, and requires dynamic evaluation to expose failures hidden by static benchmarks. We