IdioLink introduces a benchmark dataset and evaluation showing that strong embedding models struggle to retrieve equivalent meanings across idiomatic and literal forms, relying on shallow cues instead.
hub Mixed citations
Multilingual E5 Text Embeddings: A Technical Report
Mixed citation behavior. Most common role is method (43%).
49
Pith papers citing it
Method
43% of classified citations
abstract
This technical report presents the training methodology and evaluation results of the open-source multilingual E5 text embedding models, released in mid-2023. Three embedding models of different sizes (small / base / large) are provided, offering a balance between the inference efficiency and embedding quality. The training procedure adheres to the English E5 model recipe, involving contrastive pre-training on 1 billion multilingual text pairs, followed by fine-tuning on a combination of labeled datasets. Additionally, we introduce a new instruction-tuned embedding model, whose performance is on par with state-of-the-art, English-only models of similar sizes. Information regarding the model release can be found at https://github.com/microsoft/unilm/tree/master/e5 .
hub tools
citation-role summary
method 6
baseline 4
background 2
dataset 1
other 1
citation-polarity summary
representative citing papers
Co-citation predictability for statute retrieval decays over 20 years in Ukrainian court data, dropping 33-47% in MRR with non-uniform patterns across legal domains.
DAPRO provides the first dynamic, theoretically guaranteed way to allocate interaction budgets across test cases for bounding time-to-event in multi-turn LLM evaluations, achieving tighter coverage than static conformal survival methods.
EPIC trains LLMs to treat continuous embeddings as in-context prompts, yielding state-of-the-art text embedding performance on MTEB with or without prompts at inference and lower compute.
Defines ATIR task and benchmark for mixed audio-text queries; MLLM model with token compression shows substantial gains over strong baselines.
RARE builds redundancy-aware benchmarks via atomic fact decomposition and CRRF-enhanced LLM generation, showing retriever PerfRecall@10 dropping from 66.4% on general data to 5.0-27.9% on high-similarity finance/legal/patent corpora.
Code-switching creates a fundamental performance bottleneck for multilingual retrievers, causing drops of up to 27% on new benchmarks CSR-L and CS-MTEB, with embedding divergence as the key cause and vocabulary expansion insufficient to fix it.
Claim2Vec is a contrastively fine-tuned multilingual encoder that improves claim clustering performance and embedding space structure on multilingual fact-check datasets.
LMEB benchmark shows that embedding models' performance on traditional retrieval does not transfer to long-horizon memory tasks, larger models do not always perform better, and LMEB measures capabilities orthogonal to MTEB.
SQuTR aggregates 37k queries from six text retrieval datasets, synthesizes speech from 200 speakers, adds 17 noise categories at varying SNR, and shows that even large retrieval models degrade sharply under extreme acoustic noise.
Single-prompt evaluations of instruction-tuned embedding models misrepresent performance and allow any model to be ranked first by favorable prompt choice.
Embedding model performance on MTEB tasks correlates strongly with nearest-neighbor overlap and ICA magnitude differences in their embedding spaces.
Introduces the MUSA benchmark and evaluates LALMs showing that strong single-speaker performance fails to ensure robust selective attention under multilingual interference, with errors from source confusion and unresolved attribution after separation.
An extended annotation scheme with new categories and attributes plus a Gemma-300M-based multi-head classifier achieves 81.6% macro F1 on personal fact classification, outperforming few-shot LLM baselines by nearly 9 points with lower compute.
MLAIRE is a protocol that evaluates multilingual retrievers on both semantic accuracy and query-language preference using parallel passages and new metrics like LPR and Lang-nDCG, showing that standard metrics hide distinct behavioral differences among retrievers.
Iterative LLM-based refinement of category definitions improves zero-shot classification performance across 13 embedding models on a new 10-category web URL benchmark.
JFinTEB is the first benchmark for evaluating Japanese financial text embeddings across retrieval and classification tasks derived from realistic financial scenarios.
HIVE raises multimodal retrieval nDCG@10 to 41.7 on the MM-BRIGHT benchmark by inserting LLM-driven hypothesis generation and verification between retrieval passes, delivering +9.5 over the best text-only baseline and +14.1 over the best multimodal baseline.
VERTIGO post-trains camera trajectory generators with visual preference signals from Unity-rendered previews scored by a cinematically fine-tuned VLM, cutting character off-screen rates from 38% to near zero while improving framing and prompt adherence.
Retrievers trained on agent trajectories via the LRAT framework improve evidence recall, task success, and efficiency in agentic search benchmarks.
Adaptive Prompt Elicitation (APE) uses an information-theoretic framework to generate visual queries that elicit and compile user intent into better prompts for text-to-image models, showing improved alignment in benchmarks and a user study.
Proposes High-Precision Scoring (HPS) and Tie-aware Retrieval Metrics (TRM) to reduce tie-induced instability in low-precision retrieval evaluation.
Causal2Vec prepends a BERT-generated contextual token to decoder-only LLMs and pools its hidden state with the EOS token to reach new SOTA on MTEB among public-data-trained embedding models.
QCEA reformulates entity alignment as a query-conditioned ranking task with semantic encoding, graph learning, and direction-aware transformation to handle context-dependent, asymmetric correspondences in medical knowledge graphs.
citing papers explorer
-
IdioLink: Retrieving Meaning Beyond Words Across Idiomatic and Literal Expressions
IdioLink introduces a benchmark dataset and evaluation showing that strong embedding models struggle to retrieve equivalent meanings across idiomatic and literal forms, relying on shallow cues instead.
-
Temporal Decay of Co-Citation Predictability: A 20-Year Statute Retrieval Benchmark from 396M Ukrainian Court Citations
Co-citation predictability for statute retrieval decays over 20 years in Ukrainian court data, dropping 33-47% in MRR with non-uniform patterns across legal domains.
-
How Many Iterations to Jailbreak? Dynamic Budget Allocation for Multi-Turn LLM Evaluation
DAPRO provides the first dynamic, theoretically guaranteed way to allocate interaction budgets across test cases for bounding time-to-event in multi-turn LLM evaluations, achieving tighter coverage than static conformal survival methods.
-
Embedding-based In-Context Prompt Training for Enhancing LLMs as Text Encoders
EPIC trains LLMs to treat continuous embeddings as in-context prompts, yielding state-of-the-art text embedding performance on MTEB with or without prompts at inference and lower compute.
-
ATIR: Towards Audio-Text Interleaved Contextual Retrieval
Defines ATIR task and benchmark for mixed audio-text queries; MLLM model with token compression shows substantial gains over strong baselines.
-
RARE: Redundancy-Aware Retrieval Evaluation Framework for High-Similarity Corpora
RARE builds redundancy-aware benchmarks via atomic fact decomposition and CRRF-enhanced LLM generation, showing retriever PerfRecall@10 dropping from 66.4% on general data to 5.0-27.9% on high-similarity finance/legal/patent corpora.
-
Code-Switching Information Retrieval: Benchmarks, Analysis, and the Limits of Current Retrievers
Code-switching creates a fundamental performance bottleneck for multilingual retrievers, causing drops of up to 27% on new benchmarks CSR-L and CS-MTEB, with embedding divergence as the key cause and vocabulary expansion insufficient to fix it.
-
Claim2Vec: Embedding Fact-Check Claims for Multilingual Similarity and Clustering
Claim2Vec is a contrastively fine-tuned multilingual encoder that improves claim clustering performance and embedding space structure on multilingual fact-check datasets.
-
LMEB: Long-horizon Memory Embedding Benchmark
LMEB benchmark shows that embedding models' performance on traditional retrieval does not transfer to long-horizon memory tasks, larger models do not always perform better, and LMEB measures capabilities orthogonal to MTEB.
-
SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise
SQuTR aggregates 37k queries from six text retrieval datasets, synthesizes speech from 200 speakers, adds 17 noise categories at varying SNR, and shows that even large retrieval models degrade sharply under extreme acoustic noise.
-
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.
-
Structure Retention in Embedding Spaces as a Predictor of Benchmark Performance
Embedding model performance on MTEB tasks correlates strongly with nearest-neighbor overlap and ICA magnitude differences in their embedding spaces.
-
Can Large Audio Language Models Ignore Multilingual Distractors? An Evaluation of Their Selective Auditory Attention Capabilities
Introduces the MUSA benchmark and evaluates LALMs showing that strong single-speaker performance fails to ensure robust selective attention under multilingual interference, with errors from source confusion and unresolved attribution after separation.
-
An Annotation Scheme and Classifier for Personal Facts in Dialogue
An extended annotation scheme with new categories and attributes plus a Gemma-300M-based multi-head classifier achieves 81.6% macro F1 on personal fact classification, outperforming few-shot LLM baselines by nearly 9 points with lower compute.
-
MLAIRE: Multilingual Language-Aware Information Retrieval Evaluation Protocal
MLAIRE is a protocol that evaluates multilingual retrievers on both semantic accuracy and query-language preference using parallel passages and new metrics like LPR and Lang-nDCG, showing that standard metrics hide distinct behavioral differences among retrievers.
-
Iterative Definition Refinement for Zero-Shot Classification via LLM-Based Semantic Prototype Optimization
Iterative LLM-based refinement of category definitions improves zero-shot classification performance across 13 embedding models on a new 10-category web URL benchmark.
-
JFinTEB: Japanese Financial Text Embedding Benchmark
JFinTEB is the first benchmark for evaluating Japanese financial text embeddings across retrieval and classification tasks derived from realistic financial scenarios.
-
HIVE: Query, Hypothesize, Verify An LLM Framework for Multimodal Reasoning-Intensive Retrieval
HIVE raises multimodal retrieval nDCG@10 to 41.7 on the MM-BRIGHT benchmark by inserting LLM-driven hypothesis generation and verification between retrieval passes, delivering +9.5 over the best text-only baseline and +14.1 over the best multimodal baseline.
-
VERTIGO: Visual Preference Optimization for Cinematic Camera Trajectory Generation
VERTIGO post-trains camera trajectory generators with visual preference signals from Unity-rendered previews scored by a cinematically fine-tuned VLM, cutting character off-screen rates from 38% to near zero while improving framing and prompt adherence.
-
Learning to Retrieve from Agent Trajectories
Retrievers trained on agent trajectories via the LRAT framework improve evidence recall, task success, and efficiency in agentic search benchmarks.
-
Adaptive Prompt Elicitation for Text-to-Image Generation
Adaptive Prompt Elicitation (APE) uses an information-theoretic framework to generate visual queries that elicit and compile user intent into better prompts for text-to-image models, showing improved alignment in benchmarks and a user study.
-
Reliable Evaluation Protocol for Low-Precision Retrieval
Proposes High-Precision Scoring (HPS) and Tie-aware Retrieval Metrics (TRM) to reduce tie-induced instability in low-precision retrieval evaluation.
-
Causal2Vec: Improving Decoder-only LLMs as Embedding Models through a Contextual Token
Causal2Vec prepends a BERT-generated contextual token to decoder-only LLMs and pools its hidden state with the EOS token to reach new SOTA on MTEB among public-data-trained embedding models.
-
Query-Conditioned Knowledge Alignment for Reliable Cross-System Medical Reasoning
QCEA reformulates entity alignment as a query-conditioned ranking task with semantic encoding, graph learning, and direction-aware transformation to handle context-dependent, asymmetric correspondences in medical knowledge graphs.
-
QOuLiPo: What a quantum computer sees when it reads a book
Literary texts are turned into graphs for neutral-atom quantum processors, with a new rigidity metric distinguishing structural uniqueness and a QOuLiPo corpus of engineered texts created to match hardware-native graphs.
-
GRC: Unifying Reasoning-Driven Generation, Retrieval and Compression
GRC unifies generation, retrieval, and compression in LLMs via meta latent tokens for single-pass execution with modular flexibility.
-
CroSearch-R1: Better Leveraging Cross-lingual Knowledge for Retrieval-Augmented Generation
CroSearch-R1 applies search-augmented RL with cross-lingual integration and multilingual rollouts to improve RAG effectiveness on multilingual collections.
-
AffectAgent: Collaborative Multi-Agent Reasoning for Retrieval-Augmented Multimodal Emotion Recognition
AffectAgent deploys a query planner, evidence filter, and emotion generator as collaborative agents trained via MAPPO with shared reward, plus MB-MoE and RAAF modules, to achieve superior multimodal emotion recognition on MER-UniBench.
-
Human-Inspired Context-Selective Multimodal Memory for Social Robots
A new memory system for social robots selectively stores multimodal memories by emotional salience and novelty, achieving 0.506 Spearman correlation in selectivity and up to 13% better Recall@1 in multimodal retrieval.
-
Empirical Evaluation of PDF Parsing and Chunking for Financial Question Answering with RAG
Systematic tests show that specific PDF parsers combined with overlapping chunking strategies better preserve structure and improve RAG answer correctness on financial QA benchmarks including the new TableQuest dataset.
-
On the Representational Limits of Quantum-Inspired 1024-D Document Embeddings: An Experimental Evaluation Framework
Quantum-inspired 1024-D document embeddings exhibit weak, unstable ranking performance and structural geometric limitations, performing better as auxiliary components in hybrid lexical-embedding retrieval systems.
-
Cross-Lingual Attention Distillation with Personality-Informed Generative Augmentation for Multilingual Personality Recognition
ADAM uses personality-guided LLM augmentation and cross-lingual attention distillation to raise balanced accuracy on multilingual personality recognition to 0.6332 on Essays and 0.7448 on Kaggle, outperforming standard BCE loss.
-
From Exposure to Internalization: Dual-Stream Calibration for In-context Clinical Reasoning
Dual-Stream Calibration uses entropy minimization and iterative meta-learning at test time to internalize clinical evidence and outperform standard in-context learning baselines on medical tasks.
-
jina-embeddings-v5-text: Task-Targeted Embedding Distillation
A distillation-plus-task-contrastive training regimen yields compact embedding models that match or exceed state-of-the-art performance for their size while supporting 32k-token contexts and quantization.
-
Triplet Feature Fusion for Equipment Anomaly Prediction : An Open-Source Methodology Using Small Foundation Models
Triplet fusion of 28 statistical features, 64-dim time-series embeddings from a 133K-param model, and 1024-dim text embeddings into LightGBM yields 0.992 precision and 0.998 AUC on 67k HVAC samples while cutting false positives by 83%.
-
Enhancing Retrieval-Augmented Generation with Entity Linking for Educational Platforms
ELERAG integrates Wikidata entity linking with hybrid RRF re-ranking into RAG and outperforms baselines on a custom Italian academic dataset while cross-encoder methods win on the general SQuAD-it dataset.
-
Retrofitting Small Multilingual Models for Retrieval: Matching 7B Performance with 300M Parameters
A 300M multilingual embedding model matches or exceeds 7B retrieval performance via optimized data scale, hard negatives, and task diversity over language diversity.
-
Improving Korean-English Cross-Lingual Retrieval: A Data-Centric Study of Language Composition and Model Merging
Language composition in training data creates opposing effects on CLIR and mono-IR performance for Korean-English retrieval, which model merging can partially resolve.
-
SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
SmolLM2 is a 1.7B-parameter language model that outperforms Qwen2.5-1.5B and Llama3.2-1B after overtraining on 11 trillion tokens using custom FineMath, Stack-Edu, and SmolTalk datasets in a multi-stage pipeline.
-
Automated ICD Classification of Psychiatric Diagnoses: From Classical NLP to Large Language Models
Fine-tuned e5_large LLM reaches 0.866 F1_micro on ICD classification of 145k Spanish psychiatric texts, outperforming BoW, TF-IDF, and other transformers.
-
Granite Embedding Multilingual R2 Models
Granite Embedding Multilingual R2 releases 311M and 97M parameter bi-encoder models that achieve state-of-the-art retrieval performance on multilingual text, code, long-document, and reasoning datasets.
-
Pre-trained LLMs Meet Sequential Recommenders: Efficient User-Centric Knowledge Distillation
A distillation technique embeds LLM-generated textual user profiles into efficient sequential recommenders without runtime LLM inference, architectural changes, or fine-tuning.
-
Comparison of Modern Multilingual Text Embedding Techniques for Hate Speech Detection Task
Supervised models using embeddings like jina and e5 reach up to 92% accuracy on multilingual hate speech detection, substantially outperforming anomaly detection, while PCA to 64 dimensions preserves most performance in the supervised case.
-
Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
Qwen3-VL-Embedding-8B achieves state-of-the-art performance with a 77.8 overall score on the MMEB-V2 multimodal embedding benchmark.
-
KIT-TIP-NLP at MultiPride: Continual Learning with Multilingual Foundation Model
A system using XLM-RoBERTa, GPT-4 back-translation augmentation, undersampling, and language-specific threshold tuning reports 2-5% F1 gains on multilingual slur reclamation detection.
-
HR-Agents: Using Multiple LLM-based Agents to Improve Q&A about Brazilian Labor Legislation
A multi-agent LLM system using CrewAI and RAG improves response coherence and correctness over a single-LLM RAG baseline for Brazilian labor law Q&A.
- To MRL or not to MRL: Text Embeddings are Robust to Truncation Without Matryoshka Learning, Except In Heavy Truncation Scenarios
- jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers
- Kernel Affine Hull Machines as Compute-Efficient Encoders for Frozen Semantic Spaces