Information Retrieval
Papers on search engines, recommendation systems, and information extraction.
cs.IR · 379 papersVectorSmuggle: Steganographic Exfiltration in Embedding Stores and a Cryptographic Provenance Defense
VectorSmuggle reveals steganographic data exfiltration in RAG embedding stores and proposes VectorPin, a cryptographic defense for embedding integrity.
Granite Embedding Multilingual R2 Models
Granite Embedding Multilingual R2 models offer state-of-the-art dense retrieval across 200+ languages with a 32k context window.
RAG-Enhanced Large Language Models for Dynamic Content Expiration Prediction in Web Search
This paper introduces an LLM-based framework for dynamic content expiration prediction in web search, improving freshness and user experience.
Same Image, Different Meanings: Toward Retrieval of Context-Dependent Meanings
This paper explores retrieving context-dependent image meanings, observing that semantic abstraction dictates how much context is needed for accurate retrieval.
Task-Adaptive Embedding Refinement via Test-time LLM Guidance
This paper introduces an LLM-guided query refinement method that adapts embedding models in real-time for challenging zero-shot search and classification tasks.
ORBIT: Preserving Foundational Language Capabilities in GenRetrieval via Origin-Regulated Merging
ORBIT prevents catastrophic forgetting in GenRetrieval LLMs by regulating weight drift, preserving foundational language capabilities.
Question Difficulty Estimation for Large Language Models via Answer Plausibility Scoring
Q-DAPS estimates LLM question difficulty by analyzing the entropy of answer plausibility scores, outperforming baselines and aligning with human judgment.
Context Convergence Improves Answering Inferential Questions
This paper shows that constructing passages with high "context convergence" significantly improves LLM accuracy on inferential question answering tasks.
MedHopQA: A Disease-Centered Multi-Hop Reasoning Benchmark and Evaluation Framework for LLM-Based Biomedical Question Answering
MedHopQA is a new disease-centered multi-hop reasoning benchmark for evaluating LLMs in biomedical QA, designed to resist saturation and contamination.
EHR-RAGp: Retrieval-Augmented Prototype-Guided Foundation Model for Electronic Health Records
EHR-RAGp is a retrieval-augmented foundation model for EHRs, dynamically integrating relevant patient history via a prototype-guided module for better clinical predictions.
Overview of the MedHopQA track at BioCreative IX: track description, participation and evaluation of systems for multi-hop medical question answering
The MedHopQA track benchmarked LLMs on multi-hop medical QA with a new 1,000-pair dataset, highlighting RAG's importance for strong performance.
BatchBench: Toward a Workload-Aware Benchmark for Autoscaling Policies in Big Data Batch Processing -- A Proposed Framework
The paper proposes BatchBench, an open framework to benchmark diverse autoscaling policies for big data batch processing.
Unlocking Crowdsourcing for Ontology Matching Validation
This paper introduces a novel crowdsourcing system with domain-specific mechanisms to validate ontology matching, addressing challenges from LLMs.
Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models
This paper introduces Uni-AdGen, a unified autoregressive model for personalized image and text ad generation, improving realism and user preference.
Caraman at SemEval-2026 Task 8: Three-Stage Multi-Turn Retrieval with Query Rewriting, Hybrid Search, and Cross-Encoder Reranking
This paper presents a three-stage multi-turn retrieval system using query rewriting, hybrid search, and cross-encoder reranking for SemEval-2026 Task 8.
From Trajectories to Phenotypes: Disease Progression as Structural Priors for Multi-organ Imaging Representation Learning
A new framework distills disease trajectory knowledge into imaging models, significantly improving disease prediction, especially for rare conditions.
RecRM-Bench: Benchmarking Multidimensional Reward Modeling for Agentic Recommender Systems
RecRM-Bench introduces a comprehensive benchmark for multi-dimensional reward modeling in LLM-agent recommender systems, addressing current limitations.
Very Efficient Listwise Multimodal Reranking for Long Documents
ZipRerank is a highly efficient listwise multimodal reranker that significantly speeds up M-RAG for long documents by reducing input length and eliminating autoregressive decoding.
AgentDisCo: Towards Disentanglement and Collaboration in Open-ended Deep Research Agents
AgentDisCo is a novel agentic architecture that disentangles information exploration and exploitation for deep research, achieving self-refinement and strong performance.
Quality-Aware Collaborative Multi-Positive Contrastive Learning for Sequential Recommendation
QCMP-CL introduces quality-aware collaborative multi-positive contrastive learning for sequential recommendation, improving view diversity and consistency.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.