Communication and Generative Ai
A.Y. 2025/2026
Learning objectives
Within the area of computer science, students will acquire knowledge and understanding of:
- what artificial intelligence is and how it works — language models and automatic generation of images, audio and video;
- basic principles of generative models and how to interact with them (prompting);
- AI applications in digital communication;
- criticalities: reliability, bias and transparency of AI-generated contents.
- what artificial intelligence is and how it works — language models and automatic generation of images, audio and video;
- basic principles of generative models and how to interact with them (prompting);
- AI applications in digital communication;
- criticalities: reliability, bias and transparency of AI-generated contents.
Expected learning outcomes
- Using generative AI for digital communication projects.
- Writing effective prompts to get relevant and coherent results from generative models.
- Critically analysing AI-generated contents, evaluating their communicative quality, context adherence and potential bias.
- Incorporating generative AI in the writing and editing process, and in the production of multimedia contents.
- Writing effective prompts to get relevant and coherent results from generative models.
- Critically analysing AI-generated contents, evaluating their communicative quality, context adherence and potential bias.
- Incorporating generative AI in the writing and editing process, and in the production of multimedia contents.
Lesson period: First semester
Assessment methods: Esame
Assessment result: voto verbalizzato in trentesimi
Single course
This course can be attended as a single course.
Course syllabus and organization
Single session
Responsible
Lesson period
First semester
Course syllabus
The course is structured into mini-modules
Module 1 - Foundations of Artificial Intelligence and Basic Terminology
Definition of Artificial Intelligence, Machine Learning, Deep Learning, generative models, information retrieval. Basic machine-learning concepts: types of learning, data, tasks, models, and loss functions.
Module 2 - Generative Models: Development and Functioning
Architecture and training of models (Transformers, LLMs): embeddings (numerical representations), positional encoding, neural networks, and the attention mechanism. Handling word position, semantics, and context. Training phases, inference, fine-tuning. Reinforcement Learning from Human Feedback (RLHF), Retrieval-Augmented Generation (RAG), Deep Search, and hybrid models.
Module 3 - Evaluation of Generative AI Models
Metrics, benchmarks, leaderboards. Intrinsic and extrinsic evaluation. Accuracy and confusion matrix. BLEU score, BertScore. Reference datasets and open leaderboards.
Module 4 - Prompt Engineering
Management of user queries by an online LLM. Temperature and response randomization. System, role, and contextual prompting. Zero-shot, one-shot, and few-shot prompting. The RISEN methodology (Role, Instructions, Steps, End goal, Narrowing) for creating an initial prompt. Advanced prompting: Chain of Thought (CoT), Tree of Thought (ToT). Best practices in prompting and contextualization in communication.
Module 5 - Multimodal Generative AI
Overview of representations and models for image, audio, and video generation. Limits of multimodal generative AI.
Module 6 - Critical and Ethical Issues
Bias in data, models, and prompts: sources, impacts, and mitigation. Quantification and assessment of bias in LLMs. Reliability and transparency: explainability, watermarking, traceability.
Throughout the course, students will also engage in:
Hands-on prompt-engineering exercises, with a focus on use cases in digital communication and language mediation.
Critical analysis of AI-generated content.
Activities that integrate generative-AI tools into multimedia content-creation workflows.
Module 1 - Foundations of Artificial Intelligence and Basic Terminology
Definition of Artificial Intelligence, Machine Learning, Deep Learning, generative models, information retrieval. Basic machine-learning concepts: types of learning, data, tasks, models, and loss functions.
Module 2 - Generative Models: Development and Functioning
Architecture and training of models (Transformers, LLMs): embeddings (numerical representations), positional encoding, neural networks, and the attention mechanism. Handling word position, semantics, and context. Training phases, inference, fine-tuning. Reinforcement Learning from Human Feedback (RLHF), Retrieval-Augmented Generation (RAG), Deep Search, and hybrid models.
Module 3 - Evaluation of Generative AI Models
Metrics, benchmarks, leaderboards. Intrinsic and extrinsic evaluation. Accuracy and confusion matrix. BLEU score, BertScore. Reference datasets and open leaderboards.
Module 4 - Prompt Engineering
Management of user queries by an online LLM. Temperature and response randomization. System, role, and contextual prompting. Zero-shot, one-shot, and few-shot prompting. The RISEN methodology (Role, Instructions, Steps, End goal, Narrowing) for creating an initial prompt. Advanced prompting: Chain of Thought (CoT), Tree of Thought (ToT). Best practices in prompting and contextualization in communication.
Module 5 - Multimodal Generative AI
Overview of representations and models for image, audio, and video generation. Limits of multimodal generative AI.
Module 6 - Critical and Ethical Issues
Bias in data, models, and prompts: sources, impacts, and mitigation. Quantification and assessment of bias in LLMs. Reliability and transparency: explainability, watermarking, traceability.
Throughout the course, students will also engage in:
Hands-on prompt-engineering exercises, with a focus on use cases in digital communication and language mediation.
Critical analysis of AI-generated content.
Activities that integrate generative-AI tools into multimedia content-creation workflows.
Prerequisites for admission
No
Teaching methods
Lectures, group discussions, and computer-based exercises
Teaching Resources
Slides and lecture notes.
Prompt engineering book by Lee Boonstra
Prompt engineering book by Lee Boonstra
Assessment methods and Criteria
Written test
Educational website(s)
Professor(s)