140 papers
This paper introduces PT-RAG, a novel two-stage retrieval-augmented generation framework that employs cell-type-aware differentiable retrieval to significantly outperform existing methods in predicting cellular responses to gene perturbations, demonstrating that naive retrieval strategies are insufficient for this biological domain.
This research demonstrates that the sequence of rating and reviewing significantly polarizes consumer evaluations—amplifying high ratings for good services and low ratings for poor ones—by triggering affective heuristics and varying cognitive effort, a finding validated through experiments and real-world data from platforms like Yelp and Letterboxd.
The paper proposes ADC-SID, a framework that enhances robust Semantic ID generation for recommender systems by adaptively denoising skewed collaborative information through adaptive behavior-content alignment and dynamic behavioral weighting to address representation instability and poor long-tail generalization.
This paper proposes "Reading Activity Traces" (RATs) to reframe reading as a creative activity by making the interpretive labor of navigating and connecting sources visible, thereby countering the automation of human interpretation through tools like the speculative WikiRAT system.
The paper introduces LLMGreenRec, a novel multi-agent framework leveraging Large Language Models to deduce user green intents and prioritize sustainable product recommendations, thereby bridging the gap between eco-friendly intentions and actions while minimizing the system's own digital carbon footprint.
RAGPerf is an open-source, end-to-end benchmarking framework that decouples Retrieval-Augmented Generation (RAG) pipelines into modular components to enable flexible configuration, comprehensive performance and accuracy profiling, and realistic workload simulation with negligible overhead.
This paper introduces TriRec, a novel tri-party framework that leverages large language model agents to coordinate user, item, and platform interests through a two-stage process of personalized item self-promotion and multi-objective re-ranking, thereby simultaneously improving recommendation accuracy, fairness, and item utility while challenging the traditional trade-off between relevance and fairness.
This paper introduces ExBI, a novel hypergraph-based framework for Exploratory Business Intelligence that overcomes traditional limitations of static schemas and high computational costs through dynamic schema evolution and sampling-based algorithms, achieving significant speedups over existing systems like Neo4j and MySQL while maintaining high analytical accuracy.
This paper proposes Differentiable Geometric Indexing (DGI), a novel framework that resolves the optimization blockage and geometric conflicts in Generative Retrieval by employing Soft Teacher Forcing with Symmetric Weight Sharing and Isotropic Geometric Optimization to achieve superior performance, particularly in long-tail scenarios.
This paper demonstrates that replacing flat text with structured linked data, specifically enhanced entity pages featuring agent instructions and navigational affordances, significantly improves retrieval accuracy and answer quality in both standard and agentic Retrieval-Augmented Generation systems across multiple domains.
This paper surveys research on the explainability and interpretability of deep learning-based text processing and information retrieval methods, covering techniques for word embeddings, sequence modeling, attention mechanisms, transformers, BERT, and document ranking while suggesting directions for future work.
This paper proposes a unified framework for news recommendation that addresses the time-sensitive nature of user interests by combining global collaborative signals for long-term preferences with a stage-wise temporal subgraph approach, enhanced by LSTM and self-attention mechanisms, to effectively model both stable habits and rapidly evolving short-term dynamics.
This paper proposes a more efficient and effective paradigm for Generative Recommender Systems by replacing the standard interleaving of item and action tokens with two novel architectures, AttnLFA and AttnMVP, which explicitly model causal item-action dependencies to reduce sequence complexity, lower training costs, and improve recommendation performance.
This paper presents the first systematic comparison of fairness between reasoning and non-reasoning rerankers, finding that reasoning models neither improve nor harm fairness compared to traditional approaches, as they largely preserve the fairness characteristics of their input rankings.
This paper systematically disentangles the roles of feedback source and feedback model in LLM-based pseudo-relevance feedback, revealing that the choice of feedback model is critical and that the optimal feedback source depends on whether the system relies on LLM-generated text or a strong first-stage retriever.
This paper introduces a large bilingual (English/German) corpus of catalog records annotated with the Integrated Authority File (GND) and a machine-actionable GND taxonomy to enable ontology-aware multi-label classification and agent-assisted cataloging, aiming to develop transparent, authority-anchored AI tools that enhance the efficiency and scalability of subject indexing in digital libraries.
This paper introduces an interpretable, LLM-assisted pipeline that operationalizes four distinct metaphor identification protocols as executable rule scripts for Chinese, demonstrating through a comparative study that the choice of protocol is the primary source of variation in identification results while achieving competitive performance with full transparency and reproducibility.
This paper introduces PharmGraph-Auditor, a hybrid framework that combines a Virtual Knowledge Graph-based pharmaceutical knowledge base with a Chain of Verification reasoning paradigm to enable reliable, evidence-grounded, and traceable prescription auditing by transforming Large Language Models into transparent reasoning engines.
This paper introduces a novel framework for self-improving LLM agents that automatically extracts structured learnings from execution trajectories—categorizing them into strategy, recovery, and optimization tips—and injects them via adaptive memory retrieval to significantly boost task completion rates, particularly on complex scenarios.
This paper proposes a unified, query-dependent learning-to-rank model that effectively merges heterogeneous retrieval channels for large-scale e-commerce search by jointly optimizing business KPIs and capturing short-term user intent, resulting in a 2.85% conversion lift and deployment on Target.com while meeting strict latency constraints.