Information Retrieval
Papers on search engines, recommendation systems, and information extraction.
cs.IR Β· 379 papersReCoVR: Closing the Loop in Interactive Composed Video Retrieval
ReCoVR introduces a dual-pathway architecture for interactive composed video retrieval, using reflexive perception to refine search with user feedback and retrieval history.
LLM Agents Enable User-Governed Personalization Beyond Platform Boundaries
LLM agents empower users to integrate and govern their personal data across platforms, moving beyond fragmented, platform-centric personalization.
FAVOR: Efficient Filter-Agnostic Vector ANNS Based on Selectivity-Aware Exclusion Distances
FAVOR is a new ANNS method that efficiently integrates complex attribute filtering, achieving stable high throughput across varying selectivity levels.
TRACE: Tourism Recommendation with Accountable Citation Evidence
TRACE introduces a new dataset and benchmark for conversational tourism recommender systems, focusing on verifiable evidence and rejection recovery.
LARAG: Link-Aware Retrieval Strategy for RAG Systems in Hyperlinked Technical Documentation
LARAG improves RAG systems by leveraging hyperlink structures in technical documentation for more efficient and accurate content retrieval.
InterLV-Search: Benchmarking Interleaved Multimodal Agentic Search
InterLV-Search is a new benchmark for interleaved language-vision agentic search, revealing current multimodal agents struggle with complex visual evidence integration.
TCMIIES: A Browser-Based LLM-Powered Intelligent Information Extraction System for Academic Literature
TCMIIES is a browser-based, zero-installation system leveraging commercial LLMs for privacy-preserving, schema-guided information extraction from academic literature.
A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications
This survey comprehensively reviews agent skills for LLM-based agents, detailing their lifecycle, techniques, and applications to enhance scalability and robustness.
DCGL: Dual-Channel Graph Learning with Large Language Models for Knowledge-Aware Recommendation
DCGL uses dual-channel graph learning with LLMs for knowledge-aware recommendation, improving performance by decoupling semantics and behavior.
PRISM: Refracting the Entangled User Behavior Space for E-Commerce Search
PRISM disentangles user preference and item relevance in e-commerce search by explicitly modeling their interaction, improving robustness and semantic consistency.
MLAIRE: Multilingual Language-Aware Information Retrieval Evaluation Protocal
MLAIRE introduces a new protocol and metrics to evaluate multilingual information retrieval, focusing on both semantic relevance and user language preference.
DiffRetriever: Parallel Representative Tokens for Retrieval with Diffusion Language Models
DiffRetriever uses diffusion language models to generate multiple representative tokens in parallel, significantly improving retrieval performance over sequential autoregressive methods.
Topic Is Not Agenda: A Citation-Community Audit of Text Embeddings
Text embeddings fail to capture fine-grained research agendas, leading to 80% off-agenda retrievals in scientific RAG.
RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
RRCM is a ranking-driven retrieval framework for LLM recommenders that dynamically selects collaborative and metadata evidence to improve recommendation quality.
An Embarrassingly Simple Graph Heuristic Reveals Shortcut-Solvable Benchmarks for Sequential Recommendation
A simple graph heuristic reveals many sequential recommendation benchmarks are "shortcut-solvable," outperforming complex generative models.
Bridging Textual Profiles and Latent User Embeddings for Personalization
BLUE unifies interpretable textual user profiles with discriminative latent embeddings using reinforcement learning for personalized recommendations.
From Surface Learning to Deep Understanding: A Grounded AI Tutoring System for Moodle
A Moodle plugin uses RAG and LLMs for Socratic tutoring and educator content generation, ensuring high-quality, hallucination-free education.
Superintelligent Retrieval Agent: The Next Frontier of Information Retrieval
SIRA introduces a superintelligent retrieval agent that uses LLM-guided lexical queries and corpus statistics to achieve superior, efficient, single-round information retrieval.
Light-FMP: Lightweight Feature and Model Pruning for Enhanced Deep Recommender Systems
Light-FMP is a lightweight framework for deep recommender systems that prunes features and models to enhance both computational efficiency and accuracy.
GATHER: Convergence-Centric Hyper-Entity Retrieval for Zero-Shot Cell-Type Annotation
GATHER is a convergence-centric hyper-entity retriever for zero-shot cell-type annotation, efficiently identifying topological convergence points for better accuracy.
π¬ Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week β summarized, scored, and delivered to your inbox every Monday.