A new corpus of 108 mixed string-numeric tables shows that advanced tabular learners with basic string embeddings perform well on most real-world data, while large LLM encoders help on free-text heavy tables.
hub Mixed citations
arXiv preprint arXiv:2502.13595 , year=
Mixed citation behavior. Most common role is background (67%).
34
Pith papers citing it
Background
67% of classified citations
hub tools
citation-role summary
background 5
dataset 1
citation-polarity summary
representative citing papers
Tabular foundation models excel on tiny- to medium-sized IID data but are outperformed by traditional tree-based and deep learning models on non-IID, large, and high-dimensional datasets, based on evaluations across 11 models and 142 datasets in the new BeyondArena benchmark.
HAKARI-Bench reconstructs 35 benchmarks into 551 tasks across 43 languages, reproducing full MTEB, MMTEB, and BEIR rankings with Spearman correlation above 0.97 while supporting efficiency variant comparisons.
Introduces nexbax, a diagnostic framework with three themes and 10 dimensions for evaluating AI economic viability, operational practicality, and societal integrity in next-billion-user contexts.
A reference-based geometric hashing method recovers cross-model vector correspondences by exploiting local isometric consistency in contrastive embeddings and iteratively bootstrapping from a seed of paired anchors.
Multi-Level Optimal Transport (MOT) jointly infers soft layer couplings and neuron transport plans to produce global alignment scores and structured hierarchical correspondences between networks of varying depths.
MemDelta shows agent memory evaluations are confounded by LLM family and embedding model, with RAG often matching full context and self-memory underperforming basic retrieval.
BITEMBED converts LLM backbones to ternary BitNet-style encoders, adapts them with contrastive pre-training and teacher distillation, and produces text embeddings at multiple precisions that perform comparably to full-precision baselines on MMTEB.
XBCP benchmark shows deep research agents and multilingual retrievers lose accuracy, recall, calibration, and citation reliability when evidence is in non-English languages, even with gold evidence provided.
Meta-study of MTEB rankings introduces dataset-composition and ranking-scheme robustness indicators and finds only a small subset of models stay consistently strong across tasks, languages, and evaluation variations.
Introduces LOES, a constructive spectral method to select task-discriminative subspaces from intermediate layer embeddings, and GeoReg for enforcing simplicial class geometry during fine-tuning, with reported gains increasing with model depth across modalities.
Single-prompt evaluations of instruction-tuned embedding models misrepresent performance and allow any model to be ranked first by favorable prompt choice.
Agentic program search over a frozen encoder API yields retrieval programs that improve nDCG@10 on held-out tasks and unseen encoder families with no per-domain training.
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.
GELATO extends frozen Jina Embeddings v5 text models with locked non-text encoders, training only connectors to produce competitive multimodal embeddings while preserving exact text performance.
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.
COMPASS uses semantic clustering on multilingual embeddings to select auxiliary data for PEFT adapters, outperforming linguistic-similarity baselines on multilingual benchmarks while supporting continual adaptation.
SHINE trains a scalable in-context hypernetwork to generate high-quality LoRA adapters from contexts in one pass, enabling efficient LLM adaptation that saves time and compute compared to standard fine-tuning.
A 300M-parameter open embedding model sets new SOTA on MTEB for its size class and matches models twice as large while staying effective when compressed.
LEAF distills teacher-aligned student embedding models that achieve new SOTA results on BEIR and MTEB for their size class while requiring only modest data and compute.
Inverse Turing Bench evaluates LLMs on distinguishing human-human from human-AI dialogues, with GPTZero at 89.41%, Claude Opus-4.6 at 77.92%, and GPT-5.5 at 75.94% accuracy.
Sentence embeddings from language models capture semantic association effects on N400 and self-paced reading times beyond predictability, while word- and other context-based implementations do not.
PhRAG applies NER and hybrid RAG to pool fragmented industrial spare parts data into a searchable virtual stock with natural language query support.
AVA is a specialized GenAI platform for development policy research that provides verifiable syntheses from World Bank reports and is associated with 2.4-3.9 hours of weekly time savings in a large-scale user evaluation.
citing papers explorer
-
STRABLE: Benchmarking Tabular Machine Learning with Strings
A new corpus of 108 mixed string-numeric tables shows that advanced tabular learners with basic string embeddings perform well on most real-world data, while large LLM encoders help on free-text heavy tables.
-
Beyond IID: How General Are Tabular Foundation Models, Really?
Tabular foundation models excel on tiny- to medium-sized IID data but are outperformed by traditional tree-based and deep learning models on non-IID, large, and high-dimensional datasets, based on evaluations across 11 models and 142 datasets in the new BeyondArena benchmark.
-
HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions
HAKARI-Bench reconstructs 35 benchmarks into 551 tasks across 43 languages, reproducing full MTEB, MMTEB, and BEIR rankings with Spearman correlation above 0.97 while supporting efficiency variant comparisons.
-
Next-Billion AI Index: The compass for AI utility and adoption in the global majority
Introduces nexbax, a diagnostic framework with three themes and 10 dimensions for evaluating AI economic viability, operational practicality, and societal integrity in next-billion-user contexts.
-
Vector Linking via Cross-Model Local Isometric Consistency
A reference-based geometric hashing method recovers cross-model vector correspondences by exploiting local isometric consistency in contrastive embeddings and iteratively bootstrapping from a seed of paired anchors.
-
Representational Alignment Across Model Layers and Brain Regions with Multi-Level Optimal Transport
Multi-Level Optimal Transport (MOT) jointly infers soft layer couplings and neuron transport plans to produce global alignment scores and structured hierarchical correspondences between networks of varying depths.
-
MemDelta: Controlled Baselines and Hidden Confounds in Agent Memory Evaluation
MemDelta shows agent memory evaluations are confounded by LLM family and embedding model, with RAG often matching full context and self-memory underperforming basic retrieval.
-
BitNet Text Embeddings
BITEMBED converts LLM backbones to ternary BitNet-style encoders, adapts them with contrastive pre-training and teacher distillation, and produces text embeddings at multiple precisions that perform comparably to full-precision baselines on MMTEB.
-
Beyond Monolingual Deep Research: Evaluating Agents and Retrievers with Cross-Lingual BrowseComp-Plus
XBCP benchmark shows deep research agents and multilingual retrievers lose accuracy, recall, calibration, and citation reliability when evidence is in non-English languages, even with gold evidence provided.
-
On the Robustness of Multilingual Text Embedding Rankings Across Learning Tasks, Languages, and Benchmark Datasets
Meta-study of MTEB rankings introduces dataset-composition and ranking-scheme robustness indicators and finds only a small subset of models stay consistently strong across tasks, languages, and evaluation variations.
-
Uncovering the Latent Potential of Deep Intermediate Representations
Introduces LOES, a constructive spectral method to select task-discriminative subspaces from intermediate layer embeddings, and GeoReg for enforcing simplicial class geometry during fine-tuning, with reported gains increasing with model depth across modalities.
-
One prompt is not enough: Instruction Sensitivity Undermines Embedding Model Evaluation
Single-prompt evaluations of instruction-tuned embedding models misrepresent performance and allow any model to be ranked first by favorable prompt choice.
-
Test-Time Compute for Frozen Embedding Models through Agentic Program Search
Agentic program search over a frozen encoder API yields retrieval programs that improve nDCG@10 on held-out tasks and unseen encoder families with no per-domain training.
-
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.
-
jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers
GELATO extends frozen Jina Embeddings v5 text models with locked non-text encoders, training only connectors to produce competitive multimodal embeddings while preserving exact text performance.
-
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.
-
COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling
COMPASS uses semantic clustering on multilingual embeddings to select auxiliary data for PEFT adapters, outperforming linguistic-similarity baselines on multilingual benchmarks while supporting continual adaptation.
-
SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass
SHINE trains a scalable in-context hypernetwork to generate high-quality LoRA adapters from contexts in one pass, enabling efficient LLM adaptation that saves time and compute compared to standard fine-tuning.
-
EmbeddingGemma: Powerful and Lightweight Text Representations
A 300M-parameter open embedding model sets new SOTA on MTEB for its size class and matches models twice as large while staying effective when compressed.
-
LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations
LEAF distills teacher-aligned student embedding models that achieve new SOTA results on BEIR and MTEB for their size class while requiring only modest data and compute.
-
Inverse Turing Bench: Evaluating Language Models as Judges of Human vs. AI Dialogue
Inverse Turing Bench evaluates LLMs on distinguishing human-human from human-AI dialogues, with GPTZero at 89.41%, Claude Opus-4.6 at 77.92%, and GPT-5.5 at 75.94% accuracy.
-
Modeling semantic association in self-paced reading with language model embeddings
Sentence embeddings from language models capture semantic association effects on N400 and self-paced reading times beyond predictability, while word- and other context-based implementations do not.
-
Automating Information Extraction and Retrieval for Industrial Spare Parts Pooling
PhRAG applies NER and hybrid RAG to pool fragmented industrial spare parts data into a searchable virtual stock with natural language query support.
-
Learning from AVA: Early Lessons from a Curated and Trustworthy Generative AI for Policy and Development Research
AVA is a specialized GenAI platform for development policy research that provides verifiable syntheses from World Bank reports and is associated with 2.4-3.9 hours of weekly time savings in a large-scale user evaluation.
-
GovScape: A Public Multimodal Search System for 70 Million Pages of Government PDFs
GovScape delivers multimodal search over 10 million government PDFs using metadata, exact text, semantic embeddings, and visual page features at an estimated $1,500 preprocessing cost.
-
Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation (long version)
A graph-augmented RAG system with vector and graph query tools halves hallucinations and raises factual correctness scores on the MoNaCo complex QA benchmark.
-
Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini
A native multimodal embedding model from Gemini achieves reported state-of-the-art results on retrieval benchmarks across modalities via large-scale contrastive learning.
-
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.
-
Health System Scale Semantic Search Across Unstructured Clinical Notes
A semantic search system was deployed at health-system scale across 166 million clinical notes, delivering sub-second latency, ~$4000 monthly cost, and 24-89% faster chart abstraction with maintained agreement.
-
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.
-
Sifei at SemEval-2026 Task 8: Hybrid Retrieval and Query Rewriting for Multi-Turn RAG
A hybrid dense-sparse retrieval pipeline with query rewriting and cross-encoder reranking achieves 0.5453 nDCG@5 (third place) on SemEval-2026 Task 8 Task A and 0.5312 harmonic mean on Task C.
-
MIRAI: Prediction and Generation of High-Impact Academic Research
MIRAI predicts 5-year PageRank and citation impact from paper title/abstract/date with Spearman's ρ 0.47/0.62, and generates ideas judged 4:3 more impactful by LLM.
-
RAGe: A Retrieval-Augmented Generation Evaluation Framework
RAGe is a modular evaluation framework that correlates retrieval and generation quality with hardware constraints to recommend optimal RAG components for specific datasets.