SPSiska Pebiana

Siska Pebiana

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Siska Pebiana has a total of 33 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Empirical evaluation of generative fusion decoding for Indonesian general and medical speech recognition

    by Asril Jarin, Lyla Ruslana Aini, Agung Santosa, Gunarso Gunarso, Mohammad Teduh Uliniansyah, Elvira Nurfadhilah, Siska Pebiana

    This study empirically evaluates generative fusion decoding (GFD) with open-weight large language models for Indonesian automatic speech recognition (ASR) under two controlled offline conditions: general read speech (FLEURS-ID) and medical dictation (Harkit). The training-free byte-level fusion integrates three frozen language-model backends—SEA-LION, Sahabat-AI, and Mistral—with frozen Whisper-large-v3 during decoding. A development partition was used to select the static fusion weight and prompting condition, and a held-out test partition was used for final evaluation. On FLEURS-ID, the best GFD configuration reduced corpus-level word error rate (WER) from 5.91% to 4.17%, corresponding to a 29.36% relative reduction. On Harkit, it reduced WER from 15.89% to 12.30%, a 22.59% relative reduction. Paired utterance-level tests yielded p < 0.01 for both datasets. Several non-prompted configurations already improved over the unfused Whisper-large-v3 baseline, suggesting that the external language-model prior contributed more consistently than explicit prompting. Prompting produced limited changes on FLEURS-ID and larger but backend-dependent changes on Harkit. The results support GFD as a training-free decoding strategy under the evaluated conditions, while broader validation is required for noisy, spontaneous, streaming, and clinical deployment settings.

  • Safety and Reliability Evaluation of Medical Chatbots Powered by Large Language Models

    by Elvira Nurfadhilah, Lyla Ruslana Aini, Agung Santosa, Mohammad Teduh Uliniansyah, Gunarso Gunarso, Prabu Kresna Putra, Siska Pebiana, Radhiyatul Fajri, Nuraisa Novia Hidayati, Rahardito Dio Prastowo, et al.

    LLMs have new probabilistic safety problems that cannot be detected with the current benchmark measures of accuracy such as hallucination, automation bias, demographic unfairness, and privacy. In this chapter, we propose SafeMed, which is a multi-dimensional assessment framework consisting of ten dimensions for clinical safety evaluation in LLMs. SafeMed considers the following aspects: clinical accuracy, hallucination control, robustness, calibration, bias and fairness, ethics, transparency, privacy, safety of human-automation interaction, and operational feasibility. SafeMed is derived based on global standards such as WHO Guidelines for AI Ethics, EU AI Act, and FDA Good Machine Learning Practices (GMLP), and it uses Indonesian regulations as a case study involving ChatGPT-based clinical assistants, Med-PaLM, and RAG. Adversarial testing and human-in-the-loop oversight are proposed as minimum deployment standards. The chapter concludes with a practical evaluation pipeline and governance recommendations for clinicians, administrators, and policymakers.

  • Maintaining Academic Integrity in the Era of Large Language Models

    by Nuraisa Novia Hidayati, Agung Santosa, Elvira Nurfadhilah, Andi Djalal Latief, Kokoy Siti Komariah, Asril Jarin, Siska Pebiana, Yuyun Wabula, Radhiyatul Fajri, Tri Sampurno

    This chapter provides comprehensive guidance for academic researchers on effectively integrating Large Language Models (LLMs) in research workflows. Beginning with technical foundations and capabilities, it examines LLMs' architecture, training mechanisms, and specific applications in academic tasks such as text summarization, literature review, data analysis, and code generation. The chapter then offers detailed criteria for model selection and presents advanced prompt engineering techniques, including specificity guidelines, constraint formatting, chain-of-thought prompting, and in-context learning approaches. Particular attention is given to ensuring academic integrity through robust reasoning frameworks, validation protocols, and ethical considerations regarding plagiarism and transparency. The chapter concludes with systematic approaches to critical evaluation, including quality assessment criteria, adapted peer review processes, and standardized documentation practices for LLM implementation in academic research.

  • Revolutionizing Language Learning and Proficiency With Adaptive Assessments and AI-Driven System

    by Elvira Nurfadhilah, Dian Isnaeni Nurul Afra, Prabu Kresna Putra, Nimas Ayu Untariyati, Radhiyatul Fajri, Siska Pebiana, Hammam Riza

    Bilingual and multilingual education integrated with artificial intelligence (AI) has fundamentally altered conventional education paradigms, increasing the engagement of learning, individualized, and adaptive. This chapter examines AI technologies for instance Intelligent Tutoring Systems (ITS), adaptive learning algorithms, and Natural Language Processing (NLP) aid language acquisition by personalizing material delivery, offering real-time feedback, gamification, and promoting cultural competence. AI-driven curriculum caters to a variety of learning styles and boost understanding, motivation, and retention while addressing cognitive problems. However, issues such as algorithmic prejudice, data privacy, and the digital divide need fair technological access and ethical considerations. The balance of AI and human supervision is critical to developing effective learning experiences. Future breakthroughs in agentic AI will provide adaptive, context-aware interactions that improve language learning, but they must be carefully implemented to ensure inclusivity and ethical integrity.

  • The Role of AI in Language Preservation

    by Mohammad Teduh Uliniansyah, Ambar Yoganingrum, Agung Santosa, Andi Djalal Latief, Dian Isnaeni Nurul Afra, Kokoy Siti Komariah, Nimas Ayu Untariyati, Siska P. S. Pebiana, Yuyun Wabula

    This chapter discusses the role of artificial intelligence (AI) in preserving and revitalizing endangered languages. Amidst language decline caused by globalization, urbanization, and the dominance of international languages, AI is developing technologies with documentation approaches (e.g., creation of machine translation, audio recordings, written texts, and linguistic analyses) and collaboration (applications for joint activities). Despite challenges such as data scarcity and ethical issues related to indigenous knowledge, successful cases, such as the revitalization of Hawaiian and Maori, highlight the potential of AI to combat language extinction. This chapter provides valuable insights for linguists, researchers, and policymakers who advocate for interdisciplinary collaboration and the development of ethical AI that respects and preserves the rights of indigenous peoples.

  • Artificial Intelligence Technologies in Mental Health

    by Elvira Nurfadhilah, Ambar Yoganingrum, Andi Djalal Latief, Armita Widyasuri, Asril Jarin, Dian Isnaeni Nurul Afra, Gunarso Gunarso, Kokoy Siti Komariah, Mohammad Teduh Uliniansyah, Nimas Ayu Untariyati, et al.

    This chapter explores the incorporation of artificial intelligence (AI) into mental health care, with a particular focus on managing depression. AI has significantly enhanced the promotion, detection, diagnosis, treatment, and monitoring of depression by leveraging technologies such as machine learning, natural language processing, and wearable devices. This chapter also discusses various AI-driven approaches, including the analysis of questionnaires, medical records, social media, speech data, electroencephalogram, magnetic resonance imaging, chatbots, virtual reality, face analysis, robots, multimodal methods, and wearable devices. Each of these technologies offers unique benefits, such as increased accuracy in detecting depression, personalized treatment plans, and continuous patient monitoring. However, the challenges linked to AI in mental health, such as data privacy issues, biases in algorithms, and the complexity of human emotions. The chapter concludes by highlighting the opportunities and future research directions and innovation for AI in enhancing of depression care.


  • Open Access

    Twitter dataset on public sentiments towards biodiversity policy in Indonesia

    by Mohammad Teduh Uliniansyah, Indra Budi, Elvira Nurfadhilah, Dian Isnaeni Nurul Afra, Agung Santosa, Andi Djalal Latief, Asril Jarin, Gunarso, Meganingrum Arista Jiwanggi, Nuraisa Novia Hidayati, et al.