141 papers
This paper presents the first systematic study of scaling laws for reranking in information retrieval, demonstrating that performance across pointwise, pairwise, and listwise paradigms follows predictable power laws for metrics like NDCG and MAP, thereby enabling accurate forecasting of large-model performance from smaller-scale experiments to significantly reduce computational costs.
This paper proposes a deterministic and efficient GraphRAG framework that replaces non-reproducible Leiden clustering with k-core decomposition and lightweight heuristics to improve global sensemaking, answer comprehensiveness, and diversity while reducing token costs across diverse real-world datasets.
This paper proposes Time-aware Inverse Propensity Scoring (TIPS), a novel method that addresses selection and exposure biases in sequential recommendation by leveraging counterfactual reasoning to capture temporal dynamics and sequential dependencies, thereby significantly enhancing the performance of various existing recommenders.
The paper introduces DARE, a lightweight retrieval model that integrates data distribution information with function metadata to significantly improve R package retrieval and LLM agent performance in statistical analysis tasks, supported by a new knowledge base and evaluation framework.
This paper introduces CONE, a hybrid transformer encoder that utilizes a novel composite embedding algorithm to preserve the semantics of units and variables for complex numerical data, achieving state-of-the-art performance in numerical reasoning tasks across diverse domains.
This paper introduces iAgentBench, a dynamic open-domain question answering benchmark designed to evaluate the cross-source sensemaking capabilities of information-seeking agents on high-traffic topics by requiring the integration of evidence from multiple sources rather than simple retrieval.
This paper investigates temporal drift in the FreshStack retrieval benchmark by comparing 2024 and 2025 corpus snapshots, finding that while relevant documents migrate between repositories, retrieval model rankings remain highly stable, suggesting that such benchmarks can remain reliable despite temporal corpus evolution.
This study validates a Large Language Model framework that analyzes over 16,000 unstructured TripAdvisor reviews to uncover critical service quality drivers and a stark post-2022 satisfaction decline for EgyptAir that traditional metrics failed to detect, demonstrating the model's superiority in transforming passenger feedback into actionable strategic intelligence.
This paper introduces FinRetrieval, a benchmark evaluating AI agents' ability to retrieve specific financial data from structured databases, revealing that tool availability (particularly structured APIs) is the primary driver of performance while highlighting nuanced impacts of reasoning modes and geographic naming conventions.
This paper introduces SearchGym, a modular infrastructure that decouples data, embedding, and retrieval components to enable reproducible cross-platform benchmarking and hybrid search orchestration, revealing that optimal pipeline sequencing depends on filter strength and achieving a 70% Top-100 retrieval rate on the LitSearch benchmark.
This paper proposes Decoupled Promptable Sequential Recommendation (DPR), a model-agnostic framework that enables conventional sequential recommenders to dynamically steer retrieval using natural language prompts by modulating latent user representations through a specialized fusion module, Mixture-of-Experts architecture, and a three-stage training strategy, thereby achieving superior performance in intent-driven tasks without sacrificing collaborative filtering efficiency.
Pailitao-VL is a unified multi-modal retrieval system that achieves state-of-the-art, real-time industrial search performance by replacing traditional contrastive embeddings with an absolute ID-recognition paradigm and evolving reranking into a compare-and-calibrate listwise policy, thereby overcoming granularity, noise, and latency challenges in large-scale production environments.
This paper demonstrates that systematically learning embedding magnitudes by independently controlling query and document normalization significantly improves retrieval and RAG performance—particularly in out-of-domain scenarios—by revealing that magnitude encodes distinct, beneficial roles for queries and documents that are lost when assuming magnitude is noise.
This scientometric analysis of Avian Influenza research from 2014 to 2023 reveals a steady global increase in publications led by Chinese and American institutions, highlighting key journals, collaborative networks, and the predominance of original articles to underscore the necessity for continued international cooperation.
This paper proposes a scalable extension of CopulaGNN for link sign prediction that overcomes computational intractability by representing edge correlations via a Gramian of edge embeddings and reformulating conditional probabilities, thereby achieving linear convergence and competitive performance on signed graphs.
The paper introduces AMPEND-LS, an agentic multi-persona framework that synergizes Large Language Models and Small Language Models with evidence-grounded reasoning to achieve state-of-the-art, explainable, and robust multimodal fake news detection.
This paper addresses the theoretical and practical challenges of balancing similarity and diversity in dense vector retrieval by formally defining the NP-complete VRSD problem and proposing a novel parameter-free heuristic that outperforms existing methods like MMR and k-DPP.
The paper proposes LEXA, an enhanced legal case retrieval model that extends CaseGNN by integrating edge-updated graph attention, graph contrastive learning with augmentation, and contextualized LLM embeddings to fully leverage structural information and significantly outperform state-of-the-art methods.
This paper presents a comprehensive, standardized benchmark comparing RAG and GraphRAG on text-based tasks, revealing their distinct strengths and limitations while proposing hybrid integration strategies that consistently improve performance.
This paper proposes a hybrid framework that integrates Large Language Models for semantic enrichment with VARK-based cognitive profiling to effectively address cold start challenges in recommendation systems by generating personalized, explainable suggestions from minimal user data.