SOTAVerified

Semantic Retrieval

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–50 of 86 papers

TitleStatusHype
Cross-Document Cross-Lingual NLI via RST-Enhanced Graph Fusion and Interpretability Prediction—0
Semantic Retrieval Augmented Contrastive Learning for Sequential Recommendation—0
Role of Databases in GenAI Applications—0
Toward Agentic AI: Generative Information Retrieval Inspired Intelligent Communications and Networking—0
GNN-Coder: Boosting Semantic Code Retrieval with Combined GNNs and Transformer—0
AnDB: Breaking Boundaries with an AI-Native Database for Universal Semantic AnalysisCode0
Spatial-RAG: Spatial Retrieval Augmented Generation for Real-World Geospatial Reasoning Questions—0
Multimodal semantic retrieval for product searchCode0
1-800-SHARED-TASKS at RegNLP: Lexical Reranking of Semantic Retrieval (LeSeR) for Regulatory Question Answering—0
Semantic Retrieval at Walmart—0
Improving Tool Retrieval by Leveraging Large Language Models for Query Generation—0
AmazonQAC: A Large-Scale, Naturalistic Query Autocomplete Dataset—0
Athena: Retrieval-augmented Legal Judgment Prediction with Large Language Models—0
PAR: Prompt-Aware Token Reduction Method for Efficient Large Multimodal Models—0
How to Make LLMs Strong Node Classifiers?—0
LLM Agents as 6G Orchestrator: A Paradigm for Task-Oriented Physical-Layer Automation—0
Learning Spatially-Aware Language and Audio Embeddings—0
Enhancing Relevance of Embedding-based Retrieval at Walmart—0
APTNESS: Incorporating Appraisal Theory and Emotion Support Strategies for Empathetic Response GenerationCode0
UQE: A Query Engine for Unstructured Databases—0
Renal digital pathology visual knowledge search platform based on language large model and book knowledge—0
Towards an In-Depth Comprehension of Case Relevance for Better Legal Retrieval—0
Improving Cross-lingual Representation for Semantic Retrieval with Code-switching—0
Pattern retrieval of traffic congestion using graph-based associations of traffic domain-specific features—0
If the Sources Could Talk: Evaluating Large Language Models for Research Assistance in HistoryCode0
Show:102550
← PrevPage 2 of 4Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Human baselineSoft-F10.84—Unverified
2k-NN with sentence n-grams, GPT-2 embeddings, fICASoft-F10.51—Unverified
3DBTW, GPT-1 embeddings, fICASoft-F10.51—Unverified
4LSA baselineSoft-F10.39—Unverified
5Universal Sentence EncoderSoft-F10.38—Unverified
6Sentence BERTSoft-F10.31—Unverified