Text Embedding Evaluation

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, down 25% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 60

Jun 5, 2026cs.CL

Principles of Concept Representation in Sentence Encoders

What makes a sentence encoder produce good concept representations? We approach this through the lens of representational compositionality: an encoder supports a concept family only when its latent space admits a low-distortion realization of the corresponding semantic operator. This framing predicts both where current encoders succeed and where they are structurally mismatched to their supervision. Through a controlled ablation over encoder conditions trained on 3.3 million synonym and definition pairs from WordNet and Wiktionary, evaluated on three decontaminated splits and a modifier-labeled noun-phrase benchmark, we identify four principles. Fine-tuning recalibrates the latent geometry rather than expanding it (P1). Semantic signal concentrates in the final transformer layer before concept-specific training begins, making cross-layer pooling redundant (P2). Hard negatives improve discrimination and stress-test robustness without improving retrieval ranking, showing that calibration and ranking are independently addressable (P3). Finally, the effectiveness of supervision depends on the composition type of the target concept. Extensional training helps intersective and subsective families while degrading relational and intensional ones, exposing a structural limitation of current training paradigms (P4). We release two new evaluation datasets: a DBpedia semantic-gap benchmark and a modifier-labeled NP paraphrase suite.

Isabelle Mohr, John Dujany, Jonathan Souquet +1

Idiap Research Institute · Merck KGaA

Sentence Embeddings Compositional Reasoning Text Embedding Evaluation

Jun 2, 2026cs.CL

When Does Complexity Conditioning Help a Frozen Sentence Embedding? A Controlled Study of Per-Sentence and Pair-Level Difficulty Adaptation

A common intuition is that sentence embeddings should adapt to the difficulty of the input. We test this intuition in a controlled, multi-seed setting: a lightweight post-encoder adapter attaches to a frozen Qwen3-Embedding-0.6B encoder, accessing only its final pooled embedding, and is evaluated on four paraphrase and semantic-similarity tasks (PAWS, MRPC, QQP, STS-B). The naive form of the idea fails: surface-based per-sentence complexity is nearly uncorrelated with frozen-baseline error (Pearson approximately 0.05) and provides no advantage over constant or shuffled controls, while degrading a saturated baseline. Even when the target is aligned to a non-circular pair-difficulty signal, the per-sentence gate still cannot reliably capture difficulty because difficulty is primarily a property of the pair, not the individual sentence. In contrast, a small pair-level residual gated by a held-out cross-encoder difficulty signal yields consistent gains on the larger and graded tasks, including +0.022 Spearman on STS-B and +0.037 on QQP, while remaining anchored to the frozen baseline across all seeds. Because this useful form operates on sentence pairs rather than individual sentences, the resulting model is best understood as a lightweight re-ranker over cached frozen embeddings, not a replacement single-vector embedding; we make no state-of-the-art claim. Our contribution is a controlled account of when difficulty-aware adaptation helps and when it fails, together with a pre-training diagnostic that predicts the available headroom.

Suhwan Hwang

Sentence Embeddings Learning to Rank Text Embedding Evaluation

Jun 2, 2026cs.CL

SEA-LION-Embedding: Open and Reproducible Text Embeddings for Southeast Asia

Text embeddings are fundamental to many downstream applications, making robustness important for real-world NLP. However, most recent state-of-the-art embedding models are not reproducible because they rely on closed or undisclosed training data, and they remain insufficiently robust for Southeast Asian languages. We present SEA-LION-Embedding, a fully open and reproducible text-embedding pipeline for Southeast Asian languages trained only on publicly available data, and use it to study three core factors of robust embedding design: data composition, training objective, and base encoder initialization. SEA-LION-Embedding achieves state-of-the-art results on SEA-BED while enabling systematic and reproducible analysis of robust text embeddings for the region.

Peerat Limkonchotiwat, Raymond Ng, Sarana Nutanong +1

AI Singapore · School of Information Science and Technology, VISTEC

Text Embeddings Text Embedding Evaluation Text Embedding Models

May 29, 2026cs.CL

On the Robustness of Multilingual Text Embedding Rankings Across Learning Tasks, Languages, and Benchmark Datasets

Large-scale multilingual text embedding models play crucial role in both research and industry, yet their behavior in language-specific, multi-task settings remains insufficiently understood. Although benchmarking platforms such as MTEB report results across more than 250 languages, conclusions about model superiority often depend on implicit choices of dataset compositions and performance aggregation methods. To address this gap, we present a meta-study of multilingual model performance robustness in MTEB, applying a diverse set of multi-criteria decision-making ranking schemes and introducing two robustness indicators: dataset-composition robustness (sensitivity of rankings to changing dataset compositions) and ranking-scheme robustness (sensitivity to aggregation method change). They enable systematic sensitivity analysis of whether benchmarking conclusions remain stable under different evaluation designs. We conduct an in-depth analysis on five languages (English, French, German, Hindi, and Spanish) across nine tasks (e.g., classification, clustering, retrieval) and release results for approximately 230 additional languages. The task-specific analyses show that large-scale LLM-based models are often robust top performers, though not uniformly (e.g., in retrieval task), while task-agnostic results reveal that only a small subset of models remains consistently strong across tasks, ranking schemes, and data subsamples.

Ana Gjorgjevikj, Barbara Koroušić Seljak, Tome Eftimov

Computer Systems Department Jožef Stefan Institute Ljubljana, Slovenia

Multilingual Language Model Evaluation Text Embedding Evaluation Language Model Robustness

May 28, 2026cs.CL

Entity-Collision: A Stratified Protocol for Attributing Retrieval Lift in Agent Memory

End-to-end agent-memory benchmarks report a single hit@k per retriever, confounding lexical leakage (uncontrolled query/gold/distractor entity overlap) with tag-mixing (preferences, services, tools averaged together). We propose entity-collision, a system-agnostic protocol that pins the BM25 floor by construction -- every distractor shares the answer's entity tokens -- and stratifies queries by discriminator tag, so any lift over BM25 is attributable to the embedder. Applied to an open-source agent-memory testbed across 5 tags x 3 embedders x 5 collision degrees with paired-bootstrap 95% CIs, the protocol reveals a two-axis pattern: a 256-d hash trigram helps only on closed-vocabulary lexical tags at deep collision; MiniLM-384 dominates both axes; and a 2.7x-parameter BGE-large does not uniformly improve on MiniLM -- it wins on intent-style queries but loses on lexical ones. Encoder capacity alone is not the binding constraint. The synthetic intent-tag null replicates on LongMemEval (n=500) as a single-session-preference recall cliff. Adaptive vector-weight routing on LoCoMo is a measured null: 11.7pp of oracle headroom exists, but no signal we tested recovers it. All 26 result tables and 37 reproduce scripts are version-controlled and verified by a public registry; the protocol is exercised on a deterministically governed memory testbed (event-sourced decision log, DAG-state-machine schema lifecycle) so every reported CI is reproducible byte-for-byte from the ingest stream.

Youwang Deng

Independent Researcher

Agent Memory Text Embedding Evaluation Memory Agent Benchmarks IR Evaluation

May 27, 2026cs.CL

The Harder Text Embedding Benchmark (HTEB): Beyond One-dimensional Static Robustness

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 introduce the Harder Text Embedding Benchmark (HTEB), a dynamic evaluation framework that challenges model robustness along three practically interpretable axes (Lexical/Stylistic, Length and Language) by stochastically transforming inputs at evaluation time with an LLM. Evaluating 16 open-weight embedding models on 32 datasets covering 42 languages under transformations validated by 4,800 individual human ratings on an English subsample, supplemented by a Spanish-source evaluation and an exploratory STS-B study of pair-level label preservation, we find three patterns: (1) Models exhibit specific, partly decoupled robustness profiles across axes. (2) Across three model families, scale increases absolute scores but does not close the gap between original and transformed evaluations. Here, scaling tends to improve specifically the Language axis. (3) English datasets are more sensitive to HTEB transformations than multilingual datasets. This demonstrates that HTEB identifies strengths and weaknesses of models along deployment-relevant axes, challenging current embedding benchmarks and arguing for multidimensional, dynamic robustness evaluation. We make the code to run HTEB publicly available.

Manuel Frank, Haithem Afli

Department of Computer Science Munster Technological University

Text Embeddings Text Embedding Evaluation Text Embedding Models

May 26, 2026cs.CL

Grounding Text Embeddings in Stakeholder Associations

Text embeddings are widely used to analyse large corpora of complex texts. However, it is unclear whether the embeddings capture the same semantic distances as the human experts using them. Ensuring alignment between embedding representations and human intentions is essential for valid analyses. We present the Stakeholder Grounding Exercise, a method for making expert associations explicit and grounding embedding model results in human understanding. In our primary case study on Danish policy issues, we find that neural text embeddings are substantially less reliable than human experts (19-26 pp gap), and that this misalignment propagates to downstream clustering performance (Spearman

ρ=0.9

between exercise ranking and cluster quality). A secondary study on US Federal AI use cases replicates the gap (16pp) in English, using a digital protocol and a different community of experts -- demonstrating that the gap is not an artefact of a single instrument or domain. The Stakeholder Grounding Exercise offers a practical method for assessing whether embedding models capture the semantic distinctions that matter most to domain experts.

Jonathan Rystrøm, Sofie Burgos-Thorsen, Zihao Fu +3

University of Oxford, UK · Institute for Wicked Problems, Denmark · The Chinese University of Hong Kong, China +2

Text Embedding Evaluation Human-in-the-Loop Evaluation

May 22, 2026cs.IR

Benchmarking Patent Embeddings: A Multi-Task Evaluation of 22 Models Across Retrieval, Classification, and Clustering

Two questions regarding practitioners' use of patent embeddings arise: (i) Does one fine-tuning recipe suffice for all downstream applications? (ii) Is fine-tuning on one patent landscape sufficient for downstream application on other landscapes? By evaluating 22 pre-trained embedding models (ranging from 22M to 12B parameters) on three tasks -- information retrieval, classification, and clustering -- on 113,148 WIPO patents for assistive technology (46,069 citation queries) and on an external DAPFAM dataset, we find that two results cast doubt on the prevailing wisdom. (i) The optimal fine-tuning recipe depends on the downstream task: cross-sectional alignment (recipe R3) provides the largest improvements to retrieval performance (+7.1% nDCG@10), whereas a combined signal recipe (recipe R4) is better suited to classification (+7.1 F1) and clustering (+10.9 V-measure); a matched data control confirms that differences in training dataset size are not a contributing factor. (ii) Single-landscape fine-tuning hampers cross-landscape information retrieval: fine-tuning on one landscape significantly degrades cross-domain retrieval for 5 of 8 model-recipe combinations on the DAPFAM corpus, with the stronger zero-shot models suffering most. While within-family scaling is consistent (Qwen3 0.6B->4B->8B; Llama-Nemotron 1B->8B), cross-family scaling is erratic; the 12B KaLM-Gemma3 is ranked 8th on TAC retrieval performance, following prefix modification. Title+Abstract+Claims is the ubiquitous best text view, and all models suffer from a 55-65% gap between IN and OUT-of-domain performance which cannot be mitigated by hybrid BM25-dense fusion. Code and evaluation framework are publicly available.

Amirhossein Yousefiramandi, Ciaran Cooney

Clarivate, Intellectual Property Barcelona, Spain 08025

Legal IR Clustering Text Embedding Evaluation Text Classification Information Retrieval IR Evaluation

May 22, 2026cs.CL

A graph-based analysis of semantic types and coercion in contextualized word embeddings

Semantic type mismatch between a noun and its context is central to coercion phenomena. This paper introduces a graph-based method to examine how lexical and contextual type information is reflected in word embeddings. We select nouns from ten semantic types, annotate corpus instances for type matching (matching vs. coercion vs. other mismatch vs. unrestricted), and construct graphs using BERT and sense-enhanced embeddings. Two metrics -- Neighbor Type Probability (NTP) and Neighbor Type Entropy (NTE) -- are proposed to analyze neighborhood type distributions. Results show that graphs constructed with sense-enhanced embeddings reflect semantic type information better, and matching and mismatch sentences can be distinguished through the proposed metrics.

Long Chen, Deniz Ekin Yavas

Heinrich Heine University Düsseldorf

Text Embeddings Text Embedding Evaluation

May 22, 2026cs.CL

Benchmarking Google Embeddings 2 against Open-Source Models for Multilingual Dense Retrieval and RAG Systems

We benchmark Google Embeddings (GE2), a Vertex-AI-hosted bi-encoder with 2,048-token context and explicit task-type conditioning, against five open-source alternatives: BGE-M3, E5-large, Multilingual-E5-large (mE5-L), LaBSE, and Paraphrase-Multilingual-MPNet (mMPNet). Evaluation covers four BEIR subsets, a synthetic Italian RAG corpus, a chunking ablation considering 5 sizes of tokens with three strategies, and per-query latency on commodity CPU hardware. GE2 ranks first on every task, achieving BEIR avg.nDCG@10 = 0.638 and IT-RAG-Bench nDCG@10 = 0.282, but at 231.6 ms median latency, it is roughly 14x slower than the fastest local models. mE5-L reaches within 0.003 nDCG of GE2 on Italian at 31 ms, making it the preferred option when sub-100 ms SLAs matter. A more striking finding concerns LaBSE, which, despite widespread multilingual deployment scores 0.188 average nDCG@10 on BEIR, below every dedicated retrieval model including mMPNet. Chunking experiments show that all six models saturate at 32-token chunks on our corpus, with semantic chunking providing measurable gains only at 16 tokens.

Stefano Cirillo, Domenico Desiato, Giuseppe Polese +1

University of Salerno · Fisciano, Salerno, Italy · University of Bari +1

Retrieval-Augmented Generation Text Embedding Evaluation Multilingual IR Text Embedding Models

May 21, 2026cs.CL

One prompt is not enough: Instruction Sensitivity Undermines Embedding Model Evaluation

Instruction embedding models have become common among state-of-the-art models, however are evaluated using a single prompt per task. The single-point evaluation ignores a main problem of the instruction-based approach namely: sensitivity to the phrasing of the instruction. We present an empirical study of prompt sensitivity across 6 embedding models, 11 datasets, and 15 task-specific prompts per dataset, a total of 990. We show that reported scores misrepresent the distribution of scores over plausible prompts. The default prompt can both systematically understate or overstate performance. Furthermore, we show that the leaderboard ranking is not robust to prompt selection: by choosing prompts favorably, any model in our study can be promoted to first place. Our findings suggest that single-prompt evaluation is insufficient for instruction-tuned embedding models and that benchmarks should incorporate prompt robustness, either by evaluating over multiple prompts or by reporting sensitivity alongside point estimates.

Yevhen Kostiuk, Kenneth Enevoldsen

Aarhus University

Prompt Sensitivity Text Embedding Evaluation Text Embedding Models Prompt Robustness

May 21, 2026cs.CL

IdioLink: Retrieving Meaning Beyond Words Across Idiomatic and Literal Expressions

Idioms pose a fundamental challenge for language models, as their meaning cannot be inferred from surface form alone. Understanding such expressions, therefore, requires semantic abstraction beyond lexical overlap. We introduce IdioLink, a retrieval benchmark designed to test whether models can link idiomatic expressions to conceptually equivalent meanings expressed in literal or paraphrased forms. IdioLink comprises 10,700 documents and 2,140 queries, spanning 107 idioms with both literal and figurative uses. Each document and query is annotated with spans that convey the core meaning. Evaluating strong embedding baselines (e.g., BGE, E5, Contriever, and Qwen), we show that current models struggle to retrieve equivalent meanings across divergent surface realizations, relying instead on topical and shallow semantic cues. IdioLink exposes key gaps in idiom-aware semantic retrieval and provides a challenging testbed for future models.

Kai Golan Hashiloni, Daniel Fadlon, Lior Livyatan +3

Data Science Institute, Reichman University, Herzliya, Israel · EfiArazi School of Computer Science, Reichman University, Herzliya, Israel · Vrije Universiteit Amsterdam, The Netherlands

Figurative Language Understanding Semantic Search Text Embedding Evaluation IR Evaluation

May 21, 2026cs.CL

Structure Retention in Embedding Spaces as a Predictor of Benchmark Performance

In this paper, we show that high-performing embedding models organize their embedding spaces in a consistent way. We evaluate 25 contemporary embedding models on five MTEB tasks spanning four diverse task categories (retrieval, bitext mining, pair classification, and summarization) in both English and multilingual settings, and reveal that nearest-neighbor overlap and magnitude differences in independent component analysis (ICA) between paired text instances strongly correlate (even up to 0.97) with performance on the given task. Ultimately, we show that embedding tasks display varying degrees of linearity and reliance on retention of local information. Our results further the understanding of embeddings, their relation to model performance, and shed light on possible future training objectives and optimizing conditional embeddings.

Amanda Myntti, Jenna Kanerva, Veronika Laippala +1

TurkuNLP, University of Turku, Finland · ELLIS Institute Finland

Text Embedding Evaluation Text Embedding Models

May 15, 2026cs.LG

To MRL or not to MRL: Text Embeddings are Robust to Truncation Without Matryoshka Learning, Except In Heavy Truncation Scenarios

Matryoshka Representation Learning (MRL) is a widely adopted approach for training text encoders so they provide useful text representations at various sizes, available by simply truncating the resulting vectors at sizes pre-determined at training time. Recent works have shown that randomly truncating text embeddings has minimal impact in downstream performance unless vectors are reduced in size by at least 70%, suggesting that embeddings are already robust to truncation without the use of MRL. However, no prior work has compared random truncation to MRL, so it is unclear how the two methods compare as effective embedding reduction methods. In this paper, we study this by applying the same truncation used by MRL to models trained with and without MRL. Our results across several models and downstream tasks show that, unless heavily truncating embeddings (i.e. reducing their size by at least 80%), truncated embeddings of non-MRL models are competitive with, and often outperform models trained with MRL. This suggests that truncation robustness may not necessarily come from MRL, and that the choice of spending the additional training cost of MRL depends on whether heavy truncation is desired. We make our code available for reproduction.

Sotaro Takeshita, Yurina Takeshita, Simone Paolo Ponzetto +1

Data and Web Science Group, University of Mannheim, Germany · Independent Researcher · NEC Laboratories Europe, Heidelberg, Germany

Text Embeddings Representation Learning Text Embedding Evaluation Matryoshka Representation Learning Text Embedding Models

May 12, 2026cs.CL

Task-Adaptive Embedding Refinement via Test-time LLM Guidance

We explore the effectiveness of an LLM-guided query refinement paradigm for extending the usability of embedding models to challenging zero-shot search and classification tasks. Our approach refines the embedding representation of a user query using feedback from a generative LLM on a small set of documents, enabling embeddings to adapt in real time to the target task. We conduct extensive experiments with state-of-the-art text embedding models across a diverse set of challenging search and classification benchmarks. Empirical results indicate that LLM-guided query refinement yields consistent gains across all models and datasets, with relative improvements of up to +25% in literature search, intent detection, key-point matching, and nuanced query-instruction following. The refined queries improve ranking quality and induce clearer binary separation across the corpus, enabling the embedding space to better reflect the nuanced, task-specific constraints of each ad-hoc user query. Importantly, this expands the range of practical settings in which embedding models can be effectively deployed, making them a compelling alternative when costly LLM pipelines are not viable at corpus-scale. We release our experimental code for reproducibility, at https://github.com/IBM/task-aware-embedding-refinement.

Ariel Gera, Shir Ashury-Tahan, Gal Bloch +2

IBM Research

Zero-Shot Text Classification Large Language Model-Guided Optimization Text Embedding Evaluation Text Embedding Models

May 8, 2026cs.CL

The Proxy Presumption: From Semantic Embeddings to Valid Social Measures

Natural Language Processing is rapidly evolving into a primary instrument for Computational Social Science, with researchers increasingly using embeddings to measure latent constructs such as novelty, creativity, and bias. However, this transition faces a fundamental validity challenge: the ''Proxy Presumption,'' or the reliance on geometric properties (e.g., cosine distance) as direct measures of social concepts. We argue that without explicit validation, unsupervised representations remain entangled mixtures of the target construct (

C

) and confounding attributes (

Z

) like topic, style, and authorship. To bridge the gap between semantic embeddings and valid social measures, we introduce the Construct Validity Protocol (CVP). Drawing on causal representation learning and psychometrics, the CVP offers a rigorous pipeline from conceptualization to quantitative verification. We further propose Counterfactual Neutralization, a novel method using LLMs to reduce confounding in embedding space. By providing a standardized Validity Suite -- including tests for discriminant, incremental, and predictive validity -- this work offers the community a toolkit to transform heuristic proxies into robust, scientifically defensible instruments.

Baishi Li, Ta Yu, Kelvin J. L. Koa +1

National University of Singapore · Asian Institute of Digital Finance

Text Embeddings Text Embedding Evaluation Computational Social Science Psychometric Validation

May 8, 2026cs.IR

Topic Is Not Agenda: A Citation-Community Audit of Text Embeddings

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.

Junseon Yoo

Pluto Labs

Text Embedding Evaluation Graph-Based Retrieval Information Retrieval IR Evaluation

May 1, 2026cs.CL

Is Textual Similarity Invariant under Machine Translation? Evidence Based on the Political Manifesto Corpus

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.

Daria Boratyn, Damian Brzyski, Albert Leśniak +5

aJagiellonian Center for Quantitative Political Science, Jagiellonian University, Kraków, Poland · bAGH University, Kraków, Poland · cJagiellonian Center for Digital Humanities, Jagiellonian University, Kraków, Poland

Semantic Textual Similarity Text Embedding Evaluation Cross-Lingual Transfer MT Evaluation

Apr 30, 2026cs.CL

Why Mean Pooling Works: Quantifying Second-Order Collapse in Text Embeddings

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.

Tomomasa Hara, Hiroto Kurita, Masaaki Imaizumi +2

Tohoku University · The University of Tokyo · Kyoto University +3

Text Embeddings Text Embedding Evaluation

Apr 23, 2026cs.CL

SemEval-2026 Task 4: Narrative Story Similarity and Narrative Representation Learning

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.

Hans Ole Hatzel, Ekaterina Artemova, Haimo Paul Stiemer +2

University of Hamburg1 · Toloka AI2 · German UDS3 +1

Semantic Textual Similarity Representation Learning Text Embedding Evaluation

Apr 23, 2026cs.CL

Finding Meaning in Embeddings: Concept Separation Curves

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.

Paul Keuren, Marc Ponsen, Robert Ayoub Bagheri

Utrecht University · Statistics Netherlands

Sentence Embeddings Text Embedding Evaluation

Apr 20, 2026cs.LG

TeleEmbedBench: A Multi-Corpus Embedding Benchmark for RAG in Telecommunications

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.

Pranshav Gajjar, Vijay K Shah

NextG Wireless Lab, North Carolina State University, Raleigh, USA

Text Embedding Evaluation Text Embedding Models IR Evaluation

Apr 19, 2026cs.LG

FLARE: Task-agnostic embedding model evaluation through a normalization process

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.

Jingzhou Jiang, Yixuan Tang, Yi Yang +1

The Hong Kong University of Science and Technology

Text Embedding Evaluation Text Embedding Models

Apr 17, 2026cs.IR

JFinTEB: Japanese Financial Text Embedding Benchmark

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.

Masahiro Suzuki, Hiroki Sakaji

Amova Asset Management Co., Ltd. · Tokyo, Japan · Hokkaido University +1

Text Embedding Evaluation Text Embedding Models IR Evaluation Finance

Apr 16, 2026cs.CL

Comparison of Modern Multilingual Text Embedding Techniques for Hate Speech Detection Task

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.

Evaldas Vaiciukynas, Paulius Danenas, Linas Ablonskis +5

Department of Information Systems, Faculty of Informatics, Kaunas University of Technology, Kaunas, Lithuania · Centre of Information Systems Design Technologies, Faculty of Informatics, Kaunas University of Technology, Kaunas, Lithuania

Sentence Embeddings Text Embedding Evaluation Hate Speech Detection Low-Resource Language Processing

Mar 13, 2026cs.CL

LMEB: Long-horizon Memory Embedding Benchmark

Memory embeddings are crucial for memory-augmented systems, such as OpenClaw, but their evaluation is underexplored in current text embedding benchmarks, which narrowly focus on traditional passage retrieval and fail to assess models' ability to handle long-horizon memory retrieval tasks involving fragmented, context-dependent, and temporally distant information. To address this gap, we introduce the Long-horizon Memory Embedding Benchmark (LMEB), a comprehensive framework for evaluating embedding models on complex, long-horizon memory retrieval. LMEB comprises 22 datasets and 193 zero-shot retrieval tasks spanning four memory types: episodic, dialogue, semantic, and procedural. These memory types differ in terms of level of abstraction and temporal dependency, capturing distinct aspects of memory retrieval that reflect the diverse challenges of the real world. We evaluate 15 widely used embedding models, ranging from hundreds of millions to ten billion parameters. The results reveal that (1) LMEB provides a reasonable level of difficulty; (2) Larger models do not always perform better; (3) LMEB and MTEB measure orthogonal capabilities. This suggests that the field has yet to converge on a universal model capable of excelling across all memory retrieval tasks, and that strong performance on traditional passage retrieval does not necessarily transfer to long-horizon memory retrieval. LMEB provides a standardized and reproducible framework that fills a key gap in memory embedding evaluation and supports future advances in long-term, context-dependent retrieval.

Xinping Zhao, Xinshuo Hu, Jiaxin Xu +9

Harbin Institute of Technology (Shenzhen) · Shenzhen Loop Area Institute (SLAI) · Peking University

Text Embedding Evaluation IR Evaluation

Dec 17, 2025cs.CV

GRAN-TED: Generating Robust, Aligned, and Nuanced Text Embedding for Diffusion Models

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/.

Bozhou Li, Sihan Yang, Yushuo Guan +6

Peking University · Kling Team, Kuaishou Technology · Xi’an Jiaotong University +1

Text Embedding Evaluation T2I Generation Text Embedding Models T2I Diffusion Models

Aug 27, 2025cs.CL

A Framework for Deductive Semantic Content Analysis at Scale in Science Education Using Text Embeddings

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.

Jonas Timmann Mjaaland, Markus Fleten Kreutzer, Halvor Tyseng +5

Center for Interdisciplinary Education, University of Oslo, NO-0316 Oslo, Norway · Laboratory of Atomic and Solid State Physics, Cornell University, Ithaca, NY 14853, USA · Department of Physics, California State University Fullerton, Fullerton, CA 92831, USA +1

Educational Technology Text Embedding Evaluation Text Embedding Models

Aug 3, 2025cs.IR

ChEmbed: Enhancing Chemical Literature Search Through Domain-Specific Text Embeddings

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.

Ali Shiraee Kasmaee, Mohammad Khodadad, Mahdi Astaraki +4

Department of Computational Science and Engineering, McMaster University, Canada · BASF Canada Inc., Canada · BASF Corporation, USA

Text Embedding Evaluation Information Retrieval Text Embedding Models

Jun 13, 2025cs.IR

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation

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.

Mahmoud Amiri, Thomas Bocklitz

Leibniz Institute of Photonic Technology, Albert-Einstein-Strasse 9, 07745 Jena, Germany · Institute of Physical Chemistry and Abbe Center of Photonics, Friedrich Schiller University Jena, Helmholtzweg 4, 07743 Jena, Germany

Document Chunking Text Embedding Evaluation Information Retrieval RAG Evaluation Evidence Retrieval