67 citations
- Shaheed Zulfiqar Ali Bhutto Institute of Science and TechnologyPK3 papers
- Ambulance Care (Sweden)SE2 papers
- Centre National de la Recherche ScientifiqueFR2 papers
- Concordia UniversityCA2 papers
- Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR)DE2 papers
- École Polytechnique Fédérale de LausanneCH2 papers
- EDF Energy (United Kingdom)GB2 papers
- Eindhoven University of TechnologyNL2 papers
- Électricité de France (France)FR2 papers
- Institut national de recherche en sciences et technologies du numériqueFR2 papers
- Politecnico di MilanoIT2 papers
- University of MilanIT2 papers
4 papers · 2 filters
SQuARE: Structured Query & Adaptive Retrieval Engine For Tabular Formats
Chinmay Gondhalekar, Urjitkumar Patel, Fang-Chun Yeh
Accurate question answering over real spreadsheets remains difficult due to multirow headers, merged cells, and unit annotations that disrupt naive chunking, while rigid SQL views…
Doğal Dil İşlemede Tokenizasyon Standartları ve Ölçümü: Türkçe Üzerinden Büyük Dil Modellerinin Karşılaştırmalı Analizi
M. Ali Bayram, Ali Arda Fincan, Ahmet Semih Gümüş +3
Tokenization is a fundamental preprocessing step in Natural Language Processing (NLP), significantly impacting the capability of large language models (LLMs) to capture linguistic…
Büyük Dil Modelleri için TR-MMLU Benchmarkı: Performans Değerlendirmesi, Zorluklar ve İyileştirme Fırsatları
M. Ali Bayram, Ali Arda Fincan, Ahmet Semih Gümüş +3
Language models have made significant advancements in understanding and generating human language, achieving remarkable success in various applications. However, evaluating these m…
MultiFinRAG: An Optimized Multimodal Retrieval-Augmented Generation (RAG) Framework for Financial Question Answering
Chinmay Gondhalekar, Urjitkumar Patel, Fang-Chun Yeh
Financial documents--such as 10-Ks, 10-Qs, and investor presentations--span hundreds of pages and combine diverse modalities, including dense narrative text, structured tables, and…