Geographical Diffusion of News in Argentina: A Point Process Analysis
This research paper investigates the rapid and largely synchronous diffusion of news across six Argentinian provinces, highlighting the significant role of social media and large press agencies in shaping national news agendas.
Reproducibility and Generalizability Issues in Using Large Language Models for Boolean Query Generation in Systematic Reviews
While large language models (LLMs) show promise for generating Boolean queries in systematic reviews, current research suffers from reproducibility and generalizability issues, highlighting the need for more transparent and robust evaluation methods.
IRLab@iKAT24：基於多面向大型語言模型查詢生成與學習稀疏檢索的對話式搜尋
本文介紹了IRLab團隊參與TREC iKAT 2024對話式搜尋評測的系統和結果，重點探討了利用多面向大型語言模型生成查詢，並結合學習稀疏檢索技術來提升對話式搜尋效能的方法。
다중 관점 LLM 쿼리 생성을 활용한 대화형 검색을 위한 학습된 희소 검색: IRLab@iKAT24
본 논문에서는 대화형 검색에서 사용자의 개인화된 정보를 활용하여 향상된 검색 결과를 제공하기 위해 다중 관점 LLM 쿼리 생성 및 학습된 희소 검색 기법을 결합한 방법을 제안합니다.
iKAT24における対話検索のための、複数視点LLMクエリ生成を用いた学習済みスパース検索
本稿では、対話検索の精度向上のため、複数視点のクエリ生成を行うMQ4CSフレームワークに、学習済みスパース検索を組み合わせた手法を提案する。
Learned Sparse Retrieval Enhanced with Multi-Aspect LLM Query Generation for Conversational Search: Findings from IRLab's Participation in iKAT24
Integrating multi-aspect query generation with advanced retrieval and reranking models, particularly learned sparse retrieval, significantly improves conversational search performance, surpassing even human-level query rewriting.
LIBER: A Novel Framework for Lifelong User Behavior Modeling in Recommender Systems Using Large Language Models
LIBER, a novel framework leveraging large language models (LLMs), effectively models lifelong user behavior for enhanced click-through rate (CTR) prediction in recommender systems by addressing limitations of existing LLM-enhanced methods.
開放獲取是否促進了跨學科引用？——開放獲取引用優勢的分解
開放獲取 (OA) 能夠促進跨學科引用，特別是在臨床醫學領域，OA 論文更容易被其他領域的研究引用。
The Impact of Gold Open Access on Interdisciplinary and Within-Discipline Citations in Natural Science Fields
Gold open access (OA) fosters knowledge transfer across disciplines by increasing both interdisciplinary and within-discipline citations in many natural science fields, with a particularly strong effect on interdisciplinary citations in clinical medicine.
G-RAG: 그래프 기반 정보 검색을 통한 재료 과학 지식 확장
G-RAG는 그래프 데이터베이스와 엔티티 연결을 활용하여 기존 RAG 시스템의 한계를 극복하고 재료 과학 분야의 정보 검색 정확도와 문맥 이해를 향상시키는 새로운 정보 검색 강화 생성(RAG) 시스템입니다.
© 2024 by Linnk AI