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.
Matryoshka representation learning
10 Pith papers cite this work, alongside 25 external citations. Polarity classification is still indexing.
10
Pith papers citing it
25
external citations · external index
citation-role summary
background 2
dataset 1
method 1
citation-polarity summary
years
2026 10verdicts
UNVERDICTED 10representative citing papers
ALU uses public data to suppress unlearning cost quadratically while characterizing distribution mismatch effects, enabling mass unlearning with maintained utility.
MatryoshkaLoRA inserts a crafted diagonal matrix P into LoRA to learn accurate nested low-rank adapters that support dynamic rank selection with minimal performance drop.
KAHM yields a compute-efficient query encoder that outperforms matched learned adapters in reconstructing a frozen Mixedbread embedding space on an Austrian-law retrieval task while delivering an 8.53x CPU speedup.
SmartVector augments embeddings with time, confidence, and relation signals plus a consolidation process, raising top-1 accuracy on versioned queries from 31% to 62% on a synthetic benchmark while cutting stale answers and calibration error.
Lightweight numerical bandits on text embeddings match or exceed LLM accuracy in contextual bandits at a fraction of the cost, with an embedding-based diagnostic to choose between them.
MIPIC trains Matryoshka representations using self-distilled intra-relational alignment and progressive information chaining, yielding competitive results on STS, NLI, and classification tasks especially at low dimensions.
LLM embeddings from clinical records, fused with tabular data via gradient-boosted trees, predict post-traumatic epilepsy at AUC-ROC 0.892 and AUPRC 0.798.
RPORec unifies LLM reasoning with a recommendation head through reasoning-augmented modeling and reinforced preference optimization to improve recommendation accuracy and interpretability.
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.
citing papers explorer
-
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.
-
Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data
ALU uses public data to suppress unlearning cost quadratically while characterizing distribution mismatch effects, enabling mass unlearning with maintained utility.
-
MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning
MatryoshkaLoRA inserts a crafted diagonal matrix P into LoRA to learn accurate nested low-rank adapters that support dynamic rank selection with minimal performance drop.
-
Kernel Affine Hull Machines as Compute-Efficient Encoders for Frozen Semantic Spaces
KAHM yields a compute-efficient query encoder that outperforms matched learned adapters in reconstructing a frozen Mixedbread embedding space on an Austrian-law retrieval task while delivering an 8.53x CPU speedup.
-
Self-Aware Vector Embeddings for Retrieval-Augmented Generation: A Neuroscience-Inspired Framework for Temporal, Confidence-Weighted, and Relational Knowledge
SmartVector augments embeddings with time, confidence, and relation signals plus a consolidation process, raising top-1 accuracy on versioned queries from 31% to 62% on a synthetic benchmark while cutting stale answers and calibration error.
-
When Do We Need LLMs? A Diagnostic for Language-Driven Bandits
Lightweight numerical bandits on text embeddings match or exceed LLM accuracy in contextual bandits at a fraction of the cost, with an embedding-based diagnostic to choose between them.
-
MIPIC: Matryoshka Representation Learning via Self-Distilled Intra-Relational and Progressive Information Chaining
MIPIC trains Matryoshka representations using self-distilled intra-relational alignment and progressive information chaining, yielding competitive results on STS, NLI, and classification tasks especially at low dimensions.
-
Predicting Post-Traumatic Epilepsy from Clinical Records using Large Language Model Embeddings
LLM embeddings from clinical records, fused with tabular data via gradient-boosted trees, predict post-traumatic epilepsy at AUC-ROC 0.892 and AUPRC 0.798.
-
Reinforced Preference Optimization for Reasoning-Augmented Recommendations
RPORec unifies LLM reasoning with a recommendation head through reasoning-augmented modeling and reinforced preference optimization to improve recommendation accuracy and interpretability.
-
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.