text-embeddings

Tag

Cards List
#text-embeddings

Semantically Rich, Metrically Affect-Blind: A Geometric Blind Spot in Modern Text Embedders

arXiv cs.CL ↗ · 2026-10-26

A paper reports a systematic gap in modern text embedders: sentiment is highly decodable via linear probes but nearly absent from their cosine-similarity metric, and proposes SISE, a tiny supervised-contrastive head that fixes this on frozen encoders.

0 favorites 0 likes
#text-embeddings

When PTQ Calibration Helps or Hurts: Dose-Driven Collapse and Validation-Gated Abstention in Quantized Text Embedders

arXiv cs.AI ↗ · 2026-10-21 Cached

This paper studies learned post-training quantization calibration for 4-bit text embedders (e5-base-v2, BGE-M3, EmbeddingGemma-300m), finding that calibration outcome ranges from gains to catastrophic collapse depending on the 'dose' of update, and proposes a validation-gated abstention rule that never selects harmful checkpoints while retaining most beneficial ones.

0 favorites 0 likes
#text-embeddings

Scaling and Distilling Text Embeddings for Better Diffusibility

Hugging Face Daily Papers ↗ · 2026-10-01 Cached

The paper shows that scaling text embeddings (e.g., swapping T5-small for T5Gemma-2-270M) greatly improves continuous diffusion language models, and that distilling the scaled embeddings into a more connected latent space makes them easier to generate — achieving Gen. PPL 17.8 that outperforms GPT-2-M.

0 favorites 0 likes
#text-embeddings

Recovering Temporal and Geographic Signals from Language Model Embeddings

arXiv cs.AI ↗ · 2026-09-10 Cached

This paper presents a black-box, model-agnostic method to analyze temporal and geographic signals in language model embeddings using simple projections, finding that embeddings encode meaningful chronological and spatial structure for interpretability and retrieval tasks.

0 favorites 0 likes
#text-embeddings

Denoising-Aware Inversion: Revealing Privacy Risks in Noise-Protected Text Embeddings

arXiv cs.LG ↗ · 2026-08-20 Cached

This paper proposes a denoising-aware embedding inversion pipeline (DAEI) that effectively attacks noise-protected text embeddings, revealing significant privacy risks and challenging the efficacy of Gaussian noise as a defense.

0 favorites 0 likes
#text-embeddings

How Far Do Simple Transformations Translate Across Text Embedding Models?

arXiv cs.LG ↗ · 2026-08-07 Cached

This arXiv paper investigates whether simple linear transformations can translate representations across nine heterogeneous text embedding models, finding that shared structure and transferability depend jointly on architecture, training objective, pooling, and data distribution, challenging the notion of universal latent compatibility.

0 favorites 0 likes
#text-embeddings

From Text to Parameters: Predicting Item Parameters from Embedding Regularization with Reliability and Design Ceilings

arXiv cs.CL ↗ · 2026-07-09 Cached

This paper proposes an evaluation framework for predicting item parameters from text embeddings using regularized regression and reliability/design ceilings. Results show that difficulty is substantially predictable from text, while discrimination and pseudo-guessing are limited by reliability, not text signal.

0 favorites 0 likes
#text-embeddings

A Comparative Study on Affective Cues in Text Embeddings Across Psychological Emotion Theories

arXiv cs.CL ↗ · 2026-06-30 Cached

This paper evaluates twelve recent text encoders on their ability to encode affective cues from three psychological emotion theories, finding that instruction-aware open-weight encoders match or exceed proprietary ones at word level, while task-tuned embeddings are superior at sentence level.

0 favorites 0 likes
#text-embeddings

Does My Embedding Reflect That $A = B$? Evaluating Mathematical Equivalence in Embedding Models

arXiv cs.CL ↗ · 2026-06-24 Cached

This paper introduces the MELD dataset for evaluating whether text embedding models capture mathematical equivalence across different terminologies, and finds that current models fail. It proposes a contrastive learning approach to align informal and formal mathematical statements, improving retrieval on both informal-formal and natural language tasks.

0 favorites 0 likes
#text-embeddings

Measuring Curriculum Alignment across Topical Coverage, Competency, and Cognitive Depth: A Longitudinal Framework Applied to CS2013 and CS2023

arXiv cs.AI ↗ · 2026-06-20 Cached

This paper presents a human-in-the-loop pipeline for measuring a computer science program's coverage of curricular guidelines, applied longitudinally to CS2013 and CS2023. The framework reveals near-constant topical coverage but a gap in cognitive depth due to the newer guideline's raised expectations.

0 favorites 0 likes
#text-embeddings

Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings

Hugging Face Daily Papers ↗ · 2026-06-05 Cached

The paper identifies that LLM text embeddings overly express high-frequency uninformative tokens and proposes EmbedFilter, a linear transformation that filters out this subspace to improve semantic representations and enable dimensionality reduction.

0 favorites 0 likes
#text-embeddings

JFinTEB: Japanese Financial Text Embedding Benchmark

arXiv cs.CL ↗ · 2026-04-20 Cached

JFinTEB introduces the first comprehensive benchmark for evaluating Japanese financial text embeddings, addressing a gap in domain-specific and language-specific evaluation resources. The benchmark includes retrieval and classification tasks evaluated across Japanese-specific, multilingual, and commercial embedding models, with datasets and evaluation framework publicly released.

0 favorites 0 likes
#text-embeddings

New and improved embedding model

OpenAI Blog ↗ · 2022-12-15 Cached

OpenAI released text-embedding-ada-002, a unified embedding model that consolidates five previous models into one with superior performance, 4x longer context (8192 tokens), smaller dimensionality (1536), and 99.8% lower pricing than previous Davinci embeddings.

0 favorites 0 likes
#text-embeddings

saattrupdan/multilingual-e5-large-instruct

Replicate Explore ↗ · 2026-10-15 Cached

Saattrupdan 提供的 multilingual-e5-large-instruct 文本嵌入模型,基于 xlm-roberta-large 初始化并通过弱监督对比预训练与指令微调,支持 100 种语言的检索与语义相似度任务。

0 favorites 0 likes
#text-embeddings

krthr/clip-embeddings

Replicate Explore ↗ · 2026-05-09 Cached

A CLIP-based embedding model hosted on Replicate that generates 768-dimensional embeddings for both images and text using the clip-vit-large-patch14 architecture, costing ~$0.00022 per run.

0 favorites 0 likes
← Back to home

Submit Feedback