Text Embedding Evaluation

Vector search and retrieval-augmented generation (RAG) rest on the assumption that cosine similarity between text embeddings reflects conceptual relatedness. We measure where this assumption breaks. We build an augmented citation graph over 3.58M scientific papers and partition it via Leiden CPM at two granularities: sub-field (L1) and research-agenda (L2, hierarchical inside each L1). Four state-of-the-art embeddings (Gemini, Qwen3-8B, Qwen3-0.6B, SPECTER2) clear the L1 bar reasonably (45-52% top-10 same-rate) but stop working at L2: only 15-21% of top-10 neighbors share the query's research agenda. In absolute terms, 8 of every 10 retrieved papers are off-agenda. The failure is universal across eight scientific domains and all four models; SPECTER2, despite its citation-based contrastive training, is the weakest. As a diagnostic probe, we test whether the same augmented graph also functions as a retrieval signal: a deliberately simple citation-count rerank reaches 57.7% top-1 L2 on top of LLM-expanded Boolean retrieval and 59.6% on top of plain BM25, on 80 curated agenda queries -- about 9 points above the best cosine retriever (Gemini, 50.6%) and 20 points above BM25 alone (39.3%). The probe isolates a slice of the agenda-matching signal the graph carries but the embeddings miss, connecting recent theoretical limits on single-vector retrieval to a concrete failure mode of scientific RAG.

We investigate the extent to which cosine similarity between paragraph embeddings is invariant under machine translation, using the Manifesto Corpus of over 2,800 political party platforms in 28 languages translated to English via the EU eTranslation service. Rather than measuring translation-induced semantic shift directly we measure the stability of pairwise similarity relationships across embedding models, and use inter-model disagreement on original-language text as a calibrated invariance threshold. This yields a per-language non-inferiority test for four hypotheses about how translation interacts with embedding choice, with verdicts that distinguish languages where translation demonstrably preserves semantic structure from those where it demonstrably degrades it and from those where the available evidence does not resolve the question. The framework is corpus- and pipeline-agnostic and extends naturally to downstream tasks. Applied to our data, it identifies ten languages with translation invariance and four with detectable distortion.

For constructing text embeddings, mean pooling, which averages token embeddings, is the standard approach. This paper examines whether mean pooling actually works well in real models. First, we note that mean pooling can collapse information beyond the first-order statistics of the token embeddings, such as second-order statistics that capture their spatial structure, potentially mapping distinct token embedding distributions to similar text embeddings. Motivated by this concern, we propose a simple metric to quantify such a collapse induced by mean pooling. Then, using this metric, we empirically measure how often this collapse occurs in actual models and texts, and find that modern text encoders are robust to this collapse. In particular, contrastive fine-tuned text encoders tend to be less prone to the collapse than their pretrained backbone models. We also find that the robustness of these text encoders lies in the concentration of token embeddings within each text. In addition, we find that robustness to the collapse, as quantified by our proposed metric, correlates with downstream task performance. Overall, our findings offer a new perspective on why modern text encoders remain effective despite relying on seemingly coarse mean pooling.

We present the shared task on narrative similarity and narrative representation learning - NSNRL (pronounced "nass-na-rel"). The task operationalizes narrative similarity as a binary classification problem: determining which of two stories is more similar to an anchor story. We introduce a novel definition of narrative similarity, compatible with both narrative theory and intuitive judgment. Based on the similarity judgments collected under this concept, we also evaluate narrative embedding representations. We collected at least two annotations each for more than 1,000 story summary triples, with each annotation being backed by at least two annotators in agreement. This paper describes the sampling and annotation process for the dataset; further, we give an overview of the submitted systems and the techniques they employ. We received a total of 71 final submissions from 46 teams across our two tracks. In our triple-based classification setup, LLM ensembles make up many of the top-scoring systems, while in the embedding setup, systems with pre- and post-processing on pretrained embedding models perform about on par with custom fine-tuned solutions. Our analysis identifies potential headroom for improvement of automated systems in both tracks. The task website includes visualizations of embeddings alongside instance-level classification results for all teams.

Sentence embedding techniques aim to encode key concepts of a sentence's meaning in a vector space. However, the majority of evaluation approaches for sentence embedding quality rely on the use of additional classifiers or downstream tasks. These additional components make it unclear whether good results stem from the embedding itself or from the classifier's behaviour. In this paper, we propose a novel method for evaluating the effectiveness of sentence embedding methods in capturing sentence-level concepts. Our approach is classifier-independent, allowing for an objective assessment of the model's performance. The approach adopted in this study involves the systematic introduction of syntactic noise and semantic negations into sentences, with the subsequent quantification of their relative effects on the resulting embeddings. The visualisation of these effects is facilitated by Concept Separation Curves, which show the model's capacity to differentiate between conceptual and surface-level variations. By leveraging data from multiple domains, employing both Dutch and English languages, and examining sentence lengths, this study offers a compelling demonstration that Concept Separation Curves provide an interpretable, reproducible, and cross-model approach for evaluating the conceptual stability of sentence embeddings.

Large language models (LLMs) are increasingly deployed in the telecommunications domain for critical tasks, relying heavily on Retrieval-Augmented Generation (RAG) to adapt general-purpose models to continuously evolving standards. However, a significant gap exists in evaluating the embedding models that power these RAG pipelines, as general-purpose benchmarks fail to capture the dense, acronym-heavy, and highly cross-referential nature of telecommunications corpora. To address this, we introduce TeleEmbedBench, the first large-scale, multi-corpus embedding benchmark designed specifically for telecommunications. The benchmark spans three heterogeneous corpora: O-RAN Alliance specifications, 3GPP release documents, and the srsRAN open-source codebase, comprising 9,000 question-chunk pairs across three standard chunk sizes (512, 1024, and 2048 tokens). To construct this dataset at scale without manual annotation bottlenecks, we employ a novel automated pipeline where one LLM generates specific queries from text chunks and a secondary LLM validates them across strict criteria. We comprehensively evaluate eight embedding models, spanning standard sentence-transformers and LLM-based embedders. Our results demonstrate that LLM-based embedders, such as Qwen3 and EmbeddingGemma, consistently and significantly outperform traditional sentence-transformers in both retrieval accuracy and robustness against cross-domain interference. Additionally, we introduce TeleEmbedBench-Clean to evaluate model robustness against noisy, incomplete user queries. Finally, our analysis reveals that while domain-specific task instructions improve embedder performance for raw source code, they paradoxically degrade retrieval performance for natural language telecommunications specifications.

When task-specific labels are not available, it becomes difficult to select an embedding model for a specific target corpus. Existing labelless measures based on kernel estimators or Gaussian mixes fail in high-dimensional space, resulting in unstable rankings. We propose a flow-based labelless representation embedding evaluation (FLARE), which utilizes normalized streams to estimate information sufficiency directly from log-likelihood and avoid distance-based density estimation. We give a finite sample boundary, indicating that the estimation error depends on the intrinsic dimension of the data manifold rather than the original embedding dimension. On 11 datasets and 8 embedders, FLARE reached Spearman's $ρ$ of 0.90 under the supervised benchmark and remained stable in high-dimensional embeddings ($d \geq 3{,}584$) as the existing labelless baseline collapsed.

We introduce JFinTEB, the first comprehensive benchmark specifically designed for evaluating Japanese financial text embeddings. Existing embedding benchmarks provide limited coverage of language-specific and domain-specific aspects found in Japanese financial texts. Our benchmark encompasses diverse task categories including retrieval and classification tasks that reflect realistic and well-defined financial text processing scenarios. The retrieval tasks leverage instruction-following datasets and financial text generation queries, while classification tasks cover sentiment analysis, document categorization, and domain-specific classification challenges derived from economic survey data. We conduct extensive evaluations across a wide range of embedding models, including Japanese-specific models of various sizes, multilingual models, and commercial embedding services. We publicly release JFinTEB datasets and evaluation framework at https://github.com/retarfi/JFinTEB to facilitate future research and provide a standardized evaluation protocol for the Japanese financial text mining community. This work addresses a critical gap in Japanese financial text processing resources and establishes a foundation for advancing domain-specific embedding research.

Online hate speech and abusive language pose a growing challenge for content moderation, especially in multilingual settings and for low-resource languages such as Lithuanian. This paper investigates to what extent modern multilingual sentence embedding models can support accurate hate speech detection in Lithuanian, Russian, and English, and how their performance depends on downstream modeling choices and feature dimensionality. We introduce LtHate, a new Lithuanian hate speech corpus derived from news portals and social networks, and benchmark six modern multilingual encoders (potion, gemma, bge, snow, jina, e5) on LtHate, RuToxic, and EnSuperset using a unified Python pipeline. For each embedding, we train both a one class HBOS anomaly detector and a two class CatBoost classifier, with and without principal component analysis (PCA) compression to 64-dimensional feature vectors. Across all datasets, two class supervised models consistently and substantially outperform one class anomaly detection, with the best configurations achieving up to 80.96% accuracy and AUC ROC of 0.887 in Lithuanian (jina), 92.19% accuracy and AUC ROC of 0.978 in Russian (e5), and 77.21% accuracy and AUC ROC of 0.859 in English (e5 with PCA). PCA compression preserves almost all discriminative power in the supervised setting, while showing some negative impact for the unsupervised anomaly detection case. These results demonstrate how modern multilingual sentence embeddings combined with gradient boosted decision trees provide robust soft-computing solutions for multilingual hate speech detection applications.

Text embeddings are central to modern information retrieval and Retrieval-Augmented Generation (RAG). While dense models derived from Large Language Models (LLMs) dominate current practice, recent work has explored quantum-inspired alternatives motivated by the geometric properties of Hilbert-like spaces and their potential to encode richer semantic structure. This paper presents an experimental framework for constructing quantum-inspired 1024-dimensional document embeddings based on overlapping windows and multi-scale aggregation. The pipeline combines semantic projections (e.g., EigAngle), circuit-inspired feature mappings, and optional teacher-student distillation, together with a fingerprinting mechanism for reproducibility and controlled evaluation. We introduce a set of diagnostic tools for hybrid retrieval, including static and dynamic interpolation between BM25 and embedding-based scores, candidate union strategies, and a conceptual alpha-oracle that provides an upper bound for score-level fusion. Experiments on controlled corpora of Italian and English documents across technical, narrative, and legal domains, using synthetic queries, show that BM25 remains a strong baseline, teacher embeddings provide stable semantic structure, and standalone quantum-inspired embeddings exhibit weak and unstable ranking signals. Distillation yields mixed effects, improving alignment in some cases but not consistently enhancing retrieval performance, while hybrid retrieval can recover competitive results when lexical and embedding-based signals are combined. Overall, the results highlight structural limitations in the geometry of quantum-inspired embeddings, including distance compression and ranking instability, and clarify their role as auxiliary components rather than standalone retrieval representations.

Embedding models are increasingly used as retrievers in memory-augmented systems, but are typically evaluated on traditional passage retrieval benchmarks. It remains unclear whether models that excel at passage retrieval can retrieve fragmented, context-dependent, and temporally distant memories. To address this gap, we introduce the Long-horizon Memory Embedding Benchmark (LMEB), comprising 22 English datasets and 193 zero-shot retrieval tasks across four memory types: episodic, dialogue, semantic, and procedural. We benchmark 30 embedding models ranging from 33M to 12B parameters. We find that no single model dominates across memory types and that evaluation scores on LMEB correlate only weakly with those on the MTEB (English, v2) retrieval subset. These findings underscore the need for benchmarks tailored to long-horizon memory retrieval. LMEB comes with a versatile, open-source evaluation framework and a public leaderboard to guide model selection and advance research on memory embeddings.

Text embeddings have become central to computational social science and psychology, enabling scalable measurement of meaning and mixed-method inference. Yet most representation learning is optimized and evaluated for prediction and retrieval, yielding a prediction-measurement gap: representations that perform well as features may be poorly suited as scientific instruments. The paper argues that scientific meaning analysis motivates a distinct family of objectives - scientific usability - emphasizing geometric legibility, interpretability and traceability to linguistic evidence, robustness to non-semantic confounds, and compatibility with regression-style inference over semantic directions. Grounded in cognitive and neuro-psychological views of meaning, the paper assesses static word embeddings and contextual transformer representations against these requirements: static spaces remain attractive for transparent measurement, whereas contextual spaces offer richer semantics but entangle meaning with other signals and exhibit geometric and interpretability issues that complicate inference. The paper then outlines a course-setting agenda around (i) geometry-first design for gradients and abstraction, including hierarchy-aware spaces constrained by psychologically privileged levels; (ii) invertible post-hoc transformations that recondition embedding geometry and reduce nuisance influence; and (iii) meaning atlases and measurement-oriented evaluation protocols for reliable and traceable semantic inference. As the field debates the limits of scale-first progress, measurement-ready representations offer a principled new frontier.

Compositionally complex solid solution electrocatalysts span vast composition spaces, and even one materials system can contain more candidate compositions than can be measured exhaustively. Here we evaluate a label-free screening strategy that represents each composition using embeddings derived from scientific texts and prioritizes candidates based on similarity to two property concepts. We compare a corpus-trained Word2Vec baseline with transformer-based embeddings, where compositions are encoded either by linear element-wise mixing or by short composition prompts. Similarities to `concept directions', the terms conductivity and dielectric, define a 2-dimensional descriptor space, and a symmetric Pareto-front selection is used to filter candidate subsets without using electrochemical labels. Performance is assessed on 15 materials libraries including noble metal alloys and multicomponent oxides. In this setting, the lightweight Word2Vec baseline, which uses a simple linear combination of element embeddings, often achieves the highest number of reductions of possible candidate compositions while staying close to the best measured performance.

The text encoder is a critical component of text-to-image and text-to-video diffusion models, fundamentally determining the semantic fidelity of the generated content. However, its development has been hindered by two major challenges: the lack of an efficient evaluation framework that reliably predicts downstream generation performance, and the difficulty of effectively adapting pretrained language models for visual synthesis. To address these issues, we introduce GRAN-TED, a paradigm to Generate Robust, Aligned, and Nuanced Text Embeddings for Diffusion models. Our contribution is twofold. First, we propose TED-6K, a novel text-only benchmark that enables efficient and robust assessment of an encoder's representational quality without requiring costly end-to-end model training. We demonstrate that performance on TED-6K, standardized via a lightweight, unified adapter, strongly correlates with an encoder's effectiveness in downstream generation tasks. Notably, under our experimental setup, compared with training a diffusion model from scratch, evaluating with TED-6K is about \textbf{750$\times$ faster}. Second, guided by this validated framework, we develop a superior text encoder using a novel two-stage training paradigm. This process involves an initial fine-tuning stage on a Multimodal Large Language Model for better visual representation, followed by a layer-wise weighting method to extract more nuanced and potent text features. Our experiments show that the resulting GRAN-TED encoder not only achieves state-of-the-art performance on TED-6K but also leads to demonstrable performance gains in text-to-image and text-to-video generation. Our TED-6K dataset and evaluation code are available at the following link: https://anonymous.4open.science/r/GRAN-TED-4FCC/.

Studying the shape of text embedding spaces enhances our understanding of model behavior and how geometry affects downstream task performance. While a range of topological and geometric metrics have been explored, they are typically analyzed in isolation, and the connections between them remain largely unknown. In this paper, we present Unified Topological Signatures (UTS) for characterizing the structure of embedding spaces. We evaluate our method across a wide range of text embedding models and retrieval datasets, finding that it outperforms individual metrics in downstream performance prediction. Through several experiments, we demonstrate that the signatures characterize embedding spaces more accurately, improve the prediction of model-specific properties and biases, and reveal novel insights into representational similarity that challenge the global claims of the Platonic Representation Hypothesis.

Qualitative content analysis of open-ended survey responses is a commonly used research method in science education. However, traditional coding approaches are often time-consuming and prone to inconsistency, especially when applied to large datasets. Existing solutions from Natural Language Processing such as supervised classifiers, topic modeling techniques, and generative large language models have limited applicability in analysis of open-ended survey responses, since they demand extensive labeled data, disrupt established qualitative workflows, and/or yield variable results. In this paper, we introduce a text embedding-based classification framework called Deductive Semantic Content Analysis (DeSCA) that requires only a handful of examples per category to run, is transparent and replicable, and fits well with standard qualitative workflows. When benchmarked against human analysis of a physics education survey consisting of 2899 open-ended responses, the method described by our framework achieves high agreement with expert human coders across ten embeddings models on a simulated exhaustive coding task, using approximately 1-2% of the total dataset for training. The method achieves lower agreement on a complete selective coding task; this performance, however, improves with fine-tuning of the text embedding model, which can be done with a small amount of additional data. We unpack these results in terms of the theoretical assumptions of text embeddings, and further demonstrate how embeddings can be used to audit previously-analyzed datasets for coding consistency. These findings demonstrate that text embedding-assisted coding can flexibly scale to thousands of responses without sacrificing interpretability, opening avenues for deductive qualitative analysis at scale.

Retrieval-Augmented Generation (RAG) systems in chemistry heavily depend on accurate and relevant retrieval of chemical literature. However, general-purpose text embedding models frequently fail to adequately represent complex chemical terminologies, resulting in suboptimal retrieval quality. Existing embedding models for chemistry are outdated, and none is tailored to chemical literature retrieval, leaving a substantial performance gap. To address this challenge, we introduce ChEmbed, the first purpose-built family of domain-adapted text embedding models engineered for chemical literature retrieval. These models are fine-tuned via contrastive learning on a dataset comprising chemistry-specific text from the PubChem, Semantic Scholar, and ChemRxiv corpora. To create effective training data, we employ large language models to synthetically generate queries, resulting in approximately 1.7 million high-quality query-passage pairs. Additionally, we augment the tokenizer by adding 900 chemically specialized tokens to previously unused slots, which reduces the fragmentation of chemical entities, such as IUPAC names. ChEmbed also maintains an 8192-token context length, enabling retrieval of longer passages than many open-source embedding models allow. Evaluated on our newly introduced ChemRxiv Retrieval benchmark, ChEmbed outperforms state-of-the-art general embedding models, raising MRR@10 from 0.781 to 0.882 (+10.1 pp). It also substantially outperforms domain-specific embedding models such as Chemical-BERT, improving MRR@10 from 0.096 to 0.882. A role-based retrieval analysis using PubChem descriptions and ChEBI annotations shows that the improvement extends to chemical-role queries. ChEmbed represents a practical, lightweight, and reproducible embedding solution that effectively improves chemical literature retrieval.

The retrieval stage of retrieval-augmented generation (RAG) for scientific question answering depends on how documents are segmented and how chunks are represented in embedding space. This dependence is especially relevant to chemistry texts, which contain dense terminology, symbolic notation, quantitative evidence, and context associated with document structure. However, benchmark-based evidence on the interaction between chunking strategy and embedding model remains limited for chemistry-specific retrieval. Using ChemQuests, a corpus of 952 question-answer pairs from 151 ChemRxiv papers across 17 chemistry subfields, we construct chunk-level, Massive Text Embedding Benchmark (MTEB)-compatible retrieval benchmarks for controlled evaluation. We first screen 41 embedding models on the external chemistry retrieval benchmarks ChemNQRetrieval and ChemHotpotQARetrieval using a geometric-mean metric at rank 10 (Geom@10), which we validate against the full retrieval-metric profile. We then evaluate shortlisted models on ChemQuests-derived tasks across five chunking strategies, seven chunk sizes, and multiple overlap settings. Embedding choice is associated with the largest observed differences in evidence retrieval, with retrieval-tuned E5, Beijing Academy of Artificial Intelligence General Embedding (BGE), and Nomic models among the strongest overall. Within the evaluated grid, medium-to-large chunks combined with fixed-token, recursive-token, or hierarchical-section chunking provide a practical starting point for the retrieval stage of chemistry-aware RAG. Low overlap was generally favored where overlap variation was evaluated.