Introduces LOES, a constructive spectral method to select task-discriminative subspaces from intermediate layer embeddings, and GeoReg for enforcing simplicial class geometry during fine-tuning, with reported gains increasing with model depth across modalities.
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing , doi =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Single-prompt evaluations of instruction-tuned embedding models misrepresent performance and allow any model to be ranked first by favorable prompt choice.
citing papers explorer
-
Uncovering the Latent Potential of Deep Intermediate Representations
Introduces LOES, a constructive spectral method to select task-discriminative subspaces from intermediate layer embeddings, and GeoReg for enforcing simplicial class geometry during fine-tuning, with reported gains increasing with model depth across modalities.
-
One prompt is not enough: Instruction Sensitivity Undermines Embedding Model Evaluation
Single-prompt evaluations of instruction-tuned embedding models misrepresent performance and allow any model to be ranked first by favorable prompt choice.
- To MRL or not to MRL: Text Embeddings are Robust to Truncation Without Matryoshka Learning, Except In Heavy Truncation Scenarios