Results (3)
Search Parameters:
Keyword: Large Language Models
Enhancing Python Code Embeddings: Fusion of Code2vec with Large Language Models
by Long H. Ngo and Jonathan Rivalan
Journal of Engineering Research and Sciences, Volume 4, Issue 1, Page # 1-7, 2025; DOI: 10.55708/js0401001
Abstract: Automated code comprehension has recently become integral to software development. Neural networks, widely employed in natural language processing tasks, can capture the semantic meanings of language by representing it in vector form. Although programming code differs from natural language, we hypothesize that neural models can learn both the syntactic and semantic attributes inherent in code.… Read More
(This article belongs to the Special Issue on Special Issue on Multidisciplinary Sciences and Advanced Technology 2024 and the Section Software Engineering – Computer Science (SEC))
Retrieval-Augmented Reliability-Aware Selective Inference for Visual Classification
by Pratheswaran Hariharan, Haiping Xu and Donghui Yan
Journal of Engineering Research and Sciences, Volume 5, Issue 9, Page # 1-14, 2026; DOI: 10.55708/js0509001
Abstract: Multimodal large language models (MLLMs) can generate fluent visual responses even when the underlying visual prediction is weak, ambiguous, or incorrect. This work presents a retrieval-augmented, reliability-aware selective inference method that evaluates the strength and consistency of visual evidence before a prediction is communicated through a downstream multimodal response. A pretrained ResNet-50 encoder extracts normalized… Read More
(This article belongs to the Special Issue on Special Issue on Digital and Engineering Transformations in Science and Technology (SI-DETST-26))
Demographic Stereotype Elicitation in LLMs through Personality and Dark Triad Trait Attribution
by Nikolaos Vasileios Oikonomou, Ioannis Palaiokrassas, Dimitrios Vasileios Oikonomou, Sofia Panagiota Chaliasou and Nikolaos Rigas
Journal of Engineering Research and Sciences, Volume 5, Issue 1, Page # 46-65, 2026; DOI: 10.55708/js0501005
Abstract: This study investigates how Large Language Models (LLMs), specifically Meta LLaMA-3.1-8B-Instruct, implicitly attribute personality and Dark Triad traits to demographic personas. By prompting the model with 660 synthetic identity descriptors (constructed from balanced combinations of gender, race, religion, and region) and standardized psychometric questionnaires, we extract Likert-scale responses and compute aggregated Big Five (EACNO) and… Read More
(This article belongs to the Special Issue on Special Issue on Multidisciplinary Sciences and Advanced Technology 2025 and the Section Artificial Intelligence – Computer Science (AIC))