138 papers
This paper presents a production-oriented, unified multilingual semantic retrieval system for Uber Eats that leverages a fine-tuned Qwen2 two-tower model with advanced loss functions and Matryoshka Representation Learning to achieve significant recall improvements across stores, dishes, and grocery items.
This paper proposes a principled token pruning framework for late-interaction retrieval models that leverages Voronoi cell estimation in hyperspace geometry to reduce index storage overhead while maintaining retrieval performance and enhancing interpretability.
This paper proposes an interpretable text-motion retrieval framework that represents 3D human motion as joint-angle pseudo-images processed by Vision Transformers and aligns them with text via a token-wise late interaction mechanism, thereby overcoming the limitations of global-embedding methods by capturing fine-grained correspondences and improving retrieval accuracy.
The TREC 2025 RAG Track advances research on trustworthy retrieval-augmented generation systems by introducing complex narrative queries, leveraging the MS MARCO V2.1 corpus, and employing a multi-faceted evaluation framework to foster innovation in context-aware, factually grounded responses.
RecThinker is an agentic framework that enhances recommendation systems by shifting from passive information processing to autonomous investigation, utilizing an Analyze-Plan-Act paradigm with specialized tools and a self-augmented training pipeline to dynamically bridge information gaps and improve reasoning accuracy.
This paper introduces RF-Mem, a novel memory retrieval framework that mimics human dual-process cognition by adaptively switching between fast familiarity-based recognition and iterative recollection-based reconstruction to achieve scalable and effective personalization in large language models.
This study audits Google's reverse image search and finds that it functions as an ineffective gatekeeper against visual misinformation, often prioritizing irrelevant content and repeated falsehoods over debunking information, particularly during the initial emergence of visual falsehoods.
The paper introduces ThinkQE, a test-time query expansion framework that enhances web search retrieval by combining a thinking-based process for deep semantic exploration with an iterative corpus-interaction strategy to refine expansions, thereby outperforming existing LLM-based and training-intensive methods on diverse benchmarks.
This paper introduces TA-Mem, a novel framework that enhances long-term conversational QA by employing tool-augmented autonomous agents to adaptively extract structured memory and dynamically select retrieval strategies, thereby overcoming the limitations of static similarity-based methods and achieving superior performance on the LoCoMo dataset.
This paper introduces AgentGEO, a diagnostic framework that identifies specific citation failure modes in Generative Engine Optimization and applies targeted, iterative repairs to achieve over 40% relative improvement in citation rates while modifying minimal content.
This paper introduces the Elastic Time Warping algorithm, which solves the time series matching problem in arbitrary metric spaces using a Hellinger kernel stretching penalty with cubic computational complexity.
This paper introduces D2AJSCC, a novel framework that enables the deployment of high-fidelity analog joint source-channel coding on standard digital transceivers by utilizing orthogonal frequency-division multiplexing as a waveform synthesizer and a differentiable neural surrogate to overcome hardware mismatches and non-differentiable operations, thereby achieving graceful degradation without requiring hardware modifications.
This keynote presentation at ECIR 2025 explores the critical interplay between a language model's internal parametric knowledge and external contextual information, focusing on diagnostic methods to identify knowledge conflicts and strategies to improve the model's ability to utilize retrieved context effectively.
The paper proposes Manifold-Consistent Graph Indexing (MCGI), a geometry-aware, disk-resident indexing method that leverages Local Intrinsic Dimensionality to dynamically adapt search strategies, achieving significantly higher throughput and lower latency than state-of-the-art baselines on billion-scale datasets by resolving the Euclidean-Geodesic mismatch in high-dimensional spaces.
This paper introduces ELERAG, an enhanced Retrieval-Augmented Generation system that integrates Wikidata-based Entity Linking and a hybrid re-ranking strategy to significantly improve factual accuracy in Italian educational question-answering, particularly outperforming standard methods in domain-specific contexts while demonstrating the importance of domain-adapted strategies.
TaoSR1 is a novel framework that enables the direct deployment of Large Language Models for e-commerce relevance search by employing a three-stage training pipeline—incorporating Chain-of-Thought fine-tuning, DPO, and GRPO—to overcome reasoning errors and hallucinations while achieving superior performance in both offline benchmarks and online human evaluations.
The paper introduces MITRA, an on-premise Retrieval-Augmented Generation (RAG) system designed to enhance knowledge retrieval in large-scale physics collaborations like CMS by employing a novel automated pipeline for document processing and a two-tiered vector database architecture to accurately answer context-aware questions while ensuring data privacy.
This study demonstrates that a custom Transformer architecture outperforms both traditional machine learning models and zero-shot generative LLMs in automatically classifying cardiac risk from large-context, unstructured Dutch electronic health records, offering a robust alternative to manual administrative coding for geriatric cardiovascular risk management.
PathoScribe is a unified retrieval-augmented large language model framework that transforms static pathology archives into an active, reasoning-enabled clinical intelligence platform, enabling natural language case retrieval, automated cohort construction, and real-time diagnostic support with high accuracy and efficiency.
This paper argues that citation visibility in generative search should be treated as a stochastic distribution requiring uncertainty estimates rather than a fixed value, demonstrating through empirical analysis of multiple AI platforms that single-run measurements are misleadingly precise and that robust statistical sampling is essential for accurate domain performance assessment.