Claim Missing Document
Check
Articles

Found 2 Documents
Search

Pengembangan dan Evaluasi Agen Virtual dengan Model Generasi Gestur berbasis Aturan Sederhana LUBIS, MUHAMMAD FIRDAUS SYAWALUDIN; ATHALLAH, MIKAIL FAUZAN; APRIONO, CATUR
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 12, No 4: Published October 2024
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v12i4.953

Abstract

ABSTRAKStudi pengembangan gestur sebelumnya telah menyoroti manfaat pendekatan berbasis deep learning untuk menghasilkan gerakan yang mirip manusia, namun, pendekatan tersebut memerlukan dastaset besar dan komputasi intensif. Model milik penulis membedakan antara dialog pendek dan panjang, menghasilkan gerakan spesifik konteks untuk percapakan pendek (salam, perpisahan, persetujuan/tidak setuju) dan gerakan berbasis emosi untuk dialog yang lebih panjang (netral, bahagia, agresif). Penulis membandingkan kinerja sistem dengan ground truth gestures, random gestures, dan idling gestures, menggunakan metrik dari GENEA Challenge. Pendekatan ini bertujuan untuk memberikan alternatif yang lebih efisien dibandingkan model deep learning. Temuan penulis diharapkan dapat berkontribusi pada pengembangan generasi gestur yang menarik meningkatkan pemahaman pengguna dalam interaksi manusia-komputer.Kata kunci: Generasi Gestur, Interaksi Manusia-Komputer, Ukuran Dialog ABSTRACTWhile previous gesture generation studies have highlighted the benefits of deep learning-based approaches for generating human-like gestures, these often require large datasets and intensive computation. Our model differentiates between short and long dialogues, generating context-specific gestures for short exchanges (e.g., greetings, farewells, agreement/disagreement) and emotionbased gestures for longer dialogues (neutral, happy, aggressive). We compare the system's performance against ground truth gestures, random gestures, and idling gestures using metrics from the GENEA Challenge. This approach aims to provide a more efficient alternative to deep learning models. Our findings are expected to contribute to the development of more engaging, responsive virtual assistants, improving user comprehension in human-computer interaction.Keywords: Gesture Generation, Human-Computer Interaction, Dialogue Size
Development of Prompting Techniques to Trigger Proactive Dialogues in Large Language Models Muhammad Firdaus Syawaludin Lubis; Cecilia Inez Reva Manurung Manurung
International Journal of Electrical, Computer, and Biomedical Engineering Vol. 4 No. 1 (2026)
Publisher : Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62146/ijecbe.v4i1.187

Abstract

The rise of Artificial Intelligence (AI) challenges the integrity of traditional educational assessments, positioning the oral examination as a robust method for verifying authentic understanding. However, its large-scale implementation is hindered by significant logistical challenges, including time, resources, and evaluation consistency. This research addresses a foundational limitation for using Large Language Models (LLMs) in automated oral exams: their inherent passivity and failure to handle ambiguity, which are critical for effective assessment. To address this critical gap, we established an experimental framework and created two specialized datasets to systematically evaluate prompting techniques designed to elicit proactivity. Using the GPT-4o model, our comparative analysis reveals that the optimal strategy is highly task-dependent: for ambiguity detection (CNP), a Proactive Chain-of-Thought (PCoT) zero-shot approach achieved a near-perfect 0.99 F1-Score; for generating clarification questions (CQG), the PCoT few-shot variant was most effective; and in target-guided scenarios, a simpler proactive prompt proved superior. These findings provide foundational insights for developing automated oral examiners capable of nuanced, human-like dialogue, thereby addressing the scalability issues of traditional assessment methods.