Information Retrieval
Papers on search engines, recommendation systems, and information extraction.
cs.IR · 379 papersHSUGA: LLM-Enhanced Recommendation with Hierarchical Semantic Understanding and Group-Aware Alignment
HSUGA improves LLM-enhanced recommendations by using hierarchical semantic understanding and group-aware alignment for better user preference modeling.
TwiSTAR:Think Fast, Think Slow, Then Act,Generative Recommendation with Adaptive Reasoning
TwiSTAR introduces an adaptive reasoning framework for generative recommendation, balancing speed and accuracy by dynamically selecting inference strategies.
Much of Geospatial Web Search Is Beyond Traditional GIS
This paper reveals that geospatial web search is far more prevalent and practically oriented than previously understood, often exceeding traditional GIS capabilities.
Neural at ArchEHR-QA 2026: One Method Fits All: Unified Prompt Optimization for Clinical QA over EHRs
Neural1.5 uses modular prompt optimization and self-consistency to achieve strong results in clinical QA over EHRs, ranking second overall.
Rethinking Agentic Search with Pi-Serini: Is Lexical Retrieval Sufficient?
Pi-Serini demonstrates that well-tuned lexical retrieval with capable LLMs can effectively support deep agentic search, outperforming dense retrievers.
Personalized Deep Research: A User-Centric Framework, Dataset, and Hybrid Evaluation for Knowledge Discovery
PDR is a user-centric framework that personalizes deep research agents by adapting retrieval and synthesis to individual user expertise and interests.
UniRank: Unified List-wise Reranking via Confidence-Ordered Denoising
UniRank unifies autoregressive and non-autoregressive reranking using confidence-ordered denoising, improving performance and user engagement.
AgentGR: Semantic-aware Agentic Group Decision-Making Simulator for Group Recommendation
AgentGR uses LLM-driven agents to simulate complex group decision-making, integrating collaborative and semantic preferences for improved group recommendations.
Every Preference Has Its Strength: Injecting Ordinal Semantics into LLM-Based Recommenders
OSA is a new LLM-based recommender framework that injects ordinal preference strength into collaborative filtering signals, improving fine-grained recommendations.
Qwen Goes Brrr: Off-the-Shelf RAG for Ukrainian Multi-Domain Document Understanding
A Qwen-based RAG system achieves high accuracy in Ukrainian multi-domain document understanding using contextual chunking and question-aware reranking.
To Redact, or not to Redact? A Local LLM Approach to Deliberative Process Privilege Classification
A local LLM approach effectively classifies deliberative process privilege in government documents, outperforming prior methods securely.
LASAR: Latent Adaptive Semantic Aligned Reasoning for Generative Recommendation
LASAR enables efficient, high-quality generative recommendation by using latent adaptive semantic aligned reasoning, significantly faster than explicit Chain-of-Thought.
ASTRA-QA: A Benchmark for Abstract Question Answering over Documents
ASTRA-QA is a new benchmark for abstract question answering over documents, providing robust evaluation for coverage, hallucination, and retrieval scope.
NumColBERT: Non-Intrusive Numeracy Injection for Late-Interaction Retrieval Models
NumColBERT improves dense retrieval for numerical queries using a non-intrusive method that enhances ColBERT without modifying its core architecture.
H-MAPS: Hierarchical Memory-Augmented Proactive Search Assistant for Scientific Literature
H-MAPS is a proactive search assistant that uses hierarchical memory to provide personalized literature recommendations, reducing cognitive load during scientific reading.
CCD-Level and Load-Aware Thread Orchestration for In-Memory Vector ANNS on Multi-Core CPUs
This paper proposes a CCD-level and load-aware thread orchestration framework to boost in-memory vector ANNS performance on multi-core CPUs.
Enhancing Healthcare Search Intent Recognition with Query Representation Learning and Session Context
Improves healthcare search intent recognition by learning query representations and leveraging session context for better accuracy.
Urban-ImageNet: A Large-Scale Multi-Modal Dataset and Evaluation Framework for Urban Space Perception
Urban-ImageNet is a new 2M+ multi-modal dataset and benchmark for evaluating AI's perception of urban spaces using social media imagery.
OpenZL: Using Graphs to Compress Smaller and Faster
OpenZL introduces a graph-based compression framework, enabling faster, smaller, and easier-to-develop application-specific compressors.
Nautilus Compass: Black-box Persona Drift Detection for Production LLM Agents
Nautilus Compass detects persona drift in black-box LLM agents using prompt-text analysis, offering an efficient and accessible memory solution.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.