SOTAVerified

Retrieval

A methodology that involves selecting relevant data or examples from a large dataset to support tasks like prediction, learning, or inference. It enhances models by providing context or additional information, often used in systems like retrieval-augmented generation or in-context learning.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1376–1400 of 14297 papers

TitleStatusHype
DataFinder: Scientific Dataset Recommendation from Natural Language DescriptionsCode1
Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural LanguageCode1
ChatCAD+: Towards a Universal and Reliable Interactive CAD using LLMsCode1
Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal EncoderCode1
Language Models Implement Simple Word2Vec-style Vector ArithmeticCode1
ConvGQR: Generative Query Reformulation for Conversational SearchCode1
C-STS: Conditional Semantic Textual SimilarityCode1
Privacy Implications of Retrieval-Based Language ModelsCode1
Training on Thin Air: Improve Image Classification with Generated DataCode1
A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation AnalysisCode1
DAPR: A Benchmark on Document-Aware Passage RetrievalCode1
SciMON: Scientific Inspiration Machines Optimized for NoveltyCode1
Polyglot or Not? Measuring Multilingual Encyclopedic Knowledge in Foundation ModelsCode1
EDIS: Entity-Driven Image Search over Multimodal Web ContentCode1
RetICL: Sequential Retrieval of In-Context Examples with Reinforcement LearningCode1
Generative Retrieval via Term Set GenerationCode1
Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge ConflictsCode1
Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical StudyCode1
Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set AlignmentCode1
How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain SettingsCode1
Empower Large Language Model to Perform Better on Industrial Domain-Specific Question AnsweringCode1
Complex Claim Verification with Evidence Retrieved in the WildCode1
Decouple knowledge from parameters for plug-and-play language modelingCode1
Enhancing Vision-Language Pre-Training with Jointly Learned Questioner and Dense CaptionerCode1
ReFIT: Relevance Feedback from a Reranker during InferenceCode1
Show:102550
← PrevPage 56 of 572Next →
All datasetsQuora Question PairsHotpotQANatural QuestionsOK-VQAInfoSeekMVKPolyvorePubMedQAPubMedQA corpus with metadataToolLensคลิปไวรัล!! ไอซ์ ปรีชญา ลืมปิดไลฟ์สดตอนอาบน้ำ ถูกแชร์กระหึ่มเน็ต

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1BM25SQueries per second183.53—Unverified
2ElasticsearchQueries per second21.8—Unverified
3BM25-PTQueries per second6.49—Unverified
4Rank-BM25Queries per second1.18—Unverified
#ModelMetricClaimedVerifiedStatus
1BM25SQueries per second20.88—Unverified
2ElasticsearchQueries per second7.11—Unverified
3Rank-BM25Queries per second0.04—Unverified
#ModelMetricClaimedVerifiedStatus
1BM25SQueries per second41.85—Unverified
2ElasticsearchQueries per second12.16—Unverified
3Rank-BM25Queries per second0.1—Unverified
#ModelMetricClaimedVerifiedStatus
1FLMRRecall@589.32—Unverified
2RA-VQARecall@582.84—Unverified
#ModelMetricClaimedVerifiedStatus
1PreFLMRRecall@562.1—Unverified
#ModelMetricClaimedVerifiedStatus
1CLIP-KIStext-to-video Mean Rank30—Unverified
#ModelMetricClaimedVerifiedStatus
1CLIP4OutfitRecall@57.59—Unverified
#ModelMetricClaimedVerifiedStatus
1MetaGen Blended RAGAccuracy (Top-1)82.1—Unverified
#ModelMetricClaimedVerifiedStatus
1MetaGen Blended RAGAccuracy (Top-1)82.1—Unverified
#ModelMetricClaimedVerifiedStatus
1COLTCOMP@84.55—Unverified
#ModelMetricClaimedVerifiedStatus
1hello0L1,121,222—Unverified