SOTAVerified

Information Retrieval

Information retrieval is the task of ranking a list of documents or search results in response to a query

( Image credit: sudhanshumittal )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 4740 papers

TitleStatusHype
Bayesian Attention Mechanism: A Probabilistic Framework for Positional Encoding and Context Length ExtrapolationCode0
Rethinking Chunk Size For Long-Document Retrieval: A Multi-Dataset AnalysisCode0
Iterative Self-Incentivization Empowers Large Language Models as Agentic SearchersCode3
REARANK: Reasoning Re-ranking Agent via Reinforcement LearningCode1
It's High Time: A Survey of Temporal Information Retrieval and Question Answering—0
Anveshana: A New Benchmark Dataset for Cross-Lingual Information Retrieval On English Queries and Sanskrit Documents—0
Modality Curation: Building Universal Embeddings for Advanced Multimodal Information RetrievalCode1
DocMMIR: A Framework for Document Multi-modal Information RetrievalCode0
DeepResearchGym: A Free, Transparent, and Reproducible Evaluation Sandbox for Deep Research—0
Likert or Not: LLM Absolute Relevance Judgments on Fine-Grained Ordinal Scales—0
POQD: Performance-Oriented Query Decomposer for Multi-vector retrievalCode1
Reinforcement Speculative Decoding for Fast Ranking—0
Intent Classification on Low-Resource Languages with Query Similarity Search—0
InstructPart: Task-Oriented Part Segmentation with Instruction Reasoning—0
Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty—0
Learning Normal Patterns in Musical Loops—0
Tools in the Loop: Quantifying Uncertainty of LLM Question Answering Systems That Use Tools—0
Don't "Overthink" Passage Reranking: Is Reasoning Truly Necessary?—0
Align-GRAG: Reasoning-Guided Dual Alignment for Graph Retrieval-Augmented Generation—0
Fixing Data That Hurts Performance: Cascading LLMs to Relabel Hard Negatives for Robust Information Retrieval—0
MiLQ: Benchmarking IR Models for Bilingual Web Search with Mixed Language Queries—0
SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory SynthesisCode4
Layer-wise Investigation of Large-Scale Self-Supervised Music Representation Models—0
Distance Adaptive Beam Search for Provably Accurate Graph-Based Nearest Neighbor SearchCode3
MIRB: Mathematical Information Retrieval BenchmarkCode0
DisastIR: A Comprehensive Information Retrieval Benchmark for Disaster ManagementCode1
Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation—0
Benchmarking the Myopic Trap: Positional Bias in Information RetrievalCode5
Bridge the Gap between Past and Future: Siamese Model Optimization for Context-Aware Document Ranking—0
NExT-Search: Rebuilding User Feedback Ecosystem for Generative AI Search—0
JIR-Arena: The First Benchmark Dataset for Just-in-time Information RecommendationCode0
Unified Cross-modal Translation of Score Images, Symbolic Music, and Performance Audio—0
UniMoCo: Unified Modality Completion for Robust Multi-Modal EmbeddingsCode0
Towards Robust Evaluation of STEM Education: Leveraging MLLMs in Project-Based Learning—0
Comparing Lexical and Semantic Vector Search Methods When Classifying Medical Documents—0
CRISP: Clustering Multi-Vector Representations for Denoising and Pruning—0
mmRAG: A Modular Benchmark for Retrieval-Augmented Generation over Text, Tables, and Knowledge GraphsCode1
On Next-Token Prediction in LLMs: How End Goals Determine the Consistency of Decoding Algorithms—0
ALOHA: Empowering Multilingual Agent for University Orientation with Hierarchical Retrieval—0
Lost in Transliteration: Bridging the Script Gap in Neural IR—0
TRAIL: Trace Reasoning and Agentic Issue Localization—0
A Mamba-based Network for Semi-supervised Singing Melody Extraction Using Confidence Binary RegularizationCode0
Hakim: Farsi Text Embedding Model—0
Evaluating LLM Metrics Through Real-World Capabilities—0
MedEIR: A Specialized Medical Embedding Model for Enhanced Information Retrieval—0
ReCDAP: Relation-Based Conditional Diffusion with Attention Pooling for Few-Shot Knowledge Graph CompletionCode1
QUPID: Quantified Understanding for Enhanced Performance, Insights, and Decisions in Korean Search Engines—0
Learning Music Audio Representations With Limited DataCode0
Artifact Sharing for Information Retrieval Research—0
QBR: A Question-Bank-Based Approach to Fine-Grained Legal Knowledge Retrieval for the General Public—0
Show:102550
← PrevPage 2 of 95Next →
All datasetsBSARDMS MARCOCQADupStackTREC-PMAmazonMSLR WEB30KMSMARCOMTEBNews HeadlinesOhsumed

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Two-tower Bi-Encoder (RoBERTa)Recall@10074.78—Unverified
2Siamese Bi-Encoder (RoBERTa)Recall@10071.63—Unverified
3BM25Recall@10051.33—Unverified
#ModelMetricClaimedVerifiedStatus
1RetroMAE v2MRR@1042.58—Unverified
2ConAE-256Time (ms)0.33—Unverified
3ConAE-128Time (ms)0.32—Unverified
#ModelMetricClaimedVerifiedStatus
1SGPT-BE-5.8BmAP@1000.16—Unverified
2TSDAEmAP@1000.15—Unverified
#ModelMetricClaimedVerifiedStatus
1hpipubcommoninfNDCG0.56—Unverified
2hpictallinfNDCG0.55—Unverified
#ModelMetricClaimedVerifiedStatus
1MINDHR@300.32—Unverified
#ModelMetricClaimedVerifiedStatus
1Distilled NetworknDCG@100.53—Unverified
#ModelMetricClaimedVerifiedStatus
1RetroMAEMRR@100.42—Unverified
#ModelMetricClaimedVerifiedStatus
1SGPT-5.8B-msmarconDCG@1050.25—Unverified
#ModelMetricClaimedVerifiedStatus
1Information Retrieval + SVM1:1 Accuracy83.79—Unverified
#ModelMetricClaimedVerifiedStatus
1BERT+CONCEPT FILTERNDCG0.25—Unverified