Global ETD Search

A study of stock return of Chinese A-share listed companies in AI sector under the impact of ChatGPT and DeepSeek events

Wang, Y.2025

tilburg Repository record for A study of stock return of Chinese A-share listed companies in AI sector under the impact of ChatGPT and DeepSeek events (opens in a new tab)

Δημιουργία Διαλογικών Δεδομένων Tραπεζικών Συναλλαγών στην Ελληνική Γλώσσα με τη χρήση Μεγάλων Γλωσσικών Μοντέλων: Συγκριτική αξιολόγηση Μοντέλων και αναγνώριση Οντοτήτων

ΠΑΠΑΪΩΑΝΝΟΥ ΙΣΙΔΩΡΑ, PAPAIOANNOU ISIDORA2026

… την δυναμική βελτίωση των διαλόγων στο μοντέλο DeepSeek-R1 και (3) την αναγκαιότητα ενίσχυσης της ποιότητας των διαλόγων στο μοντέλο LlamaKriKri-8B. Τα ευρήματα της αναγνώρισης οντοτήτων αποδεικνύουν τη συστηματικότητα και την οργάνωση των διαλόγων, σύμφωνα με τα πρότυπα δομής του προφορικού …

athens Repository record for Δημιουργία Διαλογικών Δεδομένων Tραπεζικών Συναλλαγών στην Ελληνική Γλώσσα με τη χρήση Μεγάλων Γλωσσικών Μοντέλων: Συγκριτική αξιολόγηση Μοντέλων και αναγνώριση Οντοτήτων (opens in a new tab)

How Large Language Models Are Reshaping Skills and Job Requirements for Public Health Professionals in Saudi Arabia

Alkhinjar, Mulfi2027

… Models (LLMs) such as ChatGPT, Gemini, and DeepSeek are transforming professional work across sectors by enhancing information processing and decision support. In public health, these technologies offer the potential to improve efficiency, analytical capacity, and data-driven …

claremont Repository record for How Large Language Models Are Reshaping Skills and Job Requirements for Public Health Professionals in Saudi Arabia (opens in a new tab)

Evaluation and Enhancement of Qualitative Spatial Reasoning in LLMs via Symbolic Fine-Tuning

ΧΕΛΒΑΤΖΗ ΔΗΜΗΤΡΑ, CHELVATZI DIMITRA2026

… πρόκληση. Η έρευνα επικεντρώνεται στο μοντέλο DeepSeek-R1-Distill-Qwen-7B, διερευνώντας εάν η αρχιτεκτονική του μπορεί να εκπαιδευτεί (fine-tuning) ώστε να εσωτερικεύσει τους κανόνες του Λογισμού Κύριων Κατευθύνσεων (Cardinal Direction Calculus- CDC). Η μεθοδολογία περιλαμβάνει μια εκτενή …

athens Repository record for Evaluation and Enhancement of Qualitative Spatial Reasoning in LLMs via Symbolic Fine-Tuning (opens in a new tab)

Integrating LLMs and Causal Inference: Comparing Oral Anticoagulant Effects on Thrombosis Recurrence, Bleeding Risk and Death Using MIMIC-IV Data

Ofosu, Duncan K2027

… reasoning steps and classifications using the DeepSeek-R1 API, and fine-tuning 8–14 billion parameter versions of Llama-3, Qwen-3 and Gemma-3 models with Group Relative Policy Optimization (GRPO). Qwen-3 achieved the highest accuracy on a hold-out set of synthetic notes and de-identified real …

chapman Repository record for Integrating LLMs and Causal Inference: Comparing Oral Anticoagulant Effects on Thrombosis Recurrence, Bleeding Risk and Death Using MIMIC-IV Data (opens in a new tab)

Conversational Multimodal LLMs for Food Nutritional Information Retrieval: A Systematic Evaluation

Bhatambarekar, Gayatri MilindVirginia Tech2025

… models (including GPT-4o, Qwen 2, and Qwen 2.5, DeepSeek, and LLaVA), in a zero-shot setting on two real-world datasets, Nutrition5k and MetaFood3D. To identify which types of information most improve model predictions, a structured cue ladder protocol was developed. Models first receive only the …

vt Repository record for Conversational Multimodal LLMs for Food Nutritional Information Retrieval: A Systematic Evaluation (opens in a new tab)

DeepParse: Hybrid LLM-Guided Pattern Mining for Accurate and Reproducible Log Parsing

Shetaia, Amir2026

Modern distributed systems produce massive, heterogeneous logs essential for reliability, security, and anomaly detection. Converting these free-form messages into structured templates and extracting variable fields, known as log parsing, is challenging due to evolving formats and limited labelled …

queens Repository record for DeepParse: Hybrid LLM-Guided Pattern Mining for Accurate and Reproducible Log Parsing (opens in a new tab)