Roberto Balestri

Roberto Balestri

This study quantifies gender and skin-tone bias in two widely deployed commercial image generators - Gemini Flash 2.5 Image (NanoBanana) and GPT Image 1.5 - to test the assumption that neutral prompts yield demographically neutral outputs. We generated 3,200 photorealistic images using four semantically neutral prompts. The analysis employed a rigorous pipeline combining hybrid color normalization, facial landmark masking, and perceptually uniform skin tone quantification using the Monk (MST), PERLA, and Fitzpatrick scales. Neutral prompts produced highly polarized defaults. Both models exhibited a strong "default white" bias (>96% of outputs). However, they diverged sharply on gender: Gemini favored female-presenting subjects, while GPT favored male-presenting subjects with lighter skin tones. This research provides a large-scale, comparative audit of state-of-the-art models using an illumination-aware colorimetric methodology, distinguishing aesthetic rendering from underlying pigmentation in synthetic imagery. The study demonstrates that neutral prompts function as diagnostic probes rather than neutral instructions. It offers a robust framework for auditing algorithmic visual culture and challenges the sociolinguistic assumption that unmarked language results in inclusive representation.

Roberto Balestri

This study evaluates the biases in Gemini 2.0 Flash Experimental, a state-of-the-art large language model (LLM) developed by Google, focusing on content moderation and gender disparities. By comparing its performance to ChatGPT-4o, examined in a previous work of the author, the analysis highlights some differences in ethical moderation practices. Gemini 2.0 demonstrates reduced gender bias, notably with female-specific prompts achieving a substantial rise in acceptance rates compared to results obtained by ChatGPT-4o. It adopts a more permissive stance toward sexual content and maintains relatively high acceptance rates for violent prompts, including gender-specific cases. Despite these changes, whether they constitute an improvement is debatable. While gender bias has been reduced, this reduction comes at the cost of permitting more violent content toward both males and females, potentially normalizing violence rather than mitigating harm. Male-specific prompts still generally receive higher acceptance rates than female-specific ones. These findings underscore the complexities of aligning AI systems with ethical standards, highlighting progress in reducing certain biases while raising concerns about the broader implications of the model's permissiveness. Ongoing refinements are essential to achieve moderation practices that ensure transparency, fairness, and inclusivity without amplifying harmful content.

Roberto Balestri, Guglielmo Pescatore

Serialized TV shows are built on complex storylines that can be hard to track and evolve in ways that defy straightforward analysis. This paper introduces a multi-agent system designed to extract and analyze these narrative arcs. Tested on the first season of Grey's Anatomy (ABC 2005-), the system identifies three types of arcs: Anthology (self-contained), Soap (relationship-focused), and Genre-Specific (strictly related to the series' genre). Episodic progressions of these arcs are stored in both relational and semantic (vectorial) databases, enabling structured analysis and comparison. To bridge the gap between automation and critical interpretation, the system is paired with a graphical interface that allows for human refinement using tools to enhance and visualize the data. The system performed strongly in identifying Anthology Arcs and character entities, but its reliance on textual paratexts (such as episode summaries) revealed limitations in recognizing overlapping arcs and subtler dynamics. This approach highlights the potential of combining computational and human expertise in narrative analysis. Beyond television, it offers promise for serialized written formats, where the narrative resides entirely in the text. Future work will explore the integration of multimodal inputs, such as dialogue and visuals, and expand testing across a wider range of genres to refine the system further.

Roberto Balestri

This study investigates ChatGPT-4o's multimodal content generation, highlighting significant disparities in its treatment of sexual content and nudity versus violent and drug-related themes. Detailed analysis reveals that ChatGPT-4o consistently censors sexual content and nudity, while showing leniency towards violence and drug use. Moreover, a pronounced gender bias emerges, with female-specific content facing stricter regulation compared to male-specific content. This disparity likely stems from media scrutiny and public backlash over past AI controversies, prompting tech companies to impose stringent guidelines on sensitive issues to protect their reputations. Our findings emphasize the urgent need for AI systems to uphold genuine ethical standards and accountability, transcending mere political correctness. This research contributes to the understanding of biases in AI-driven language and multimodal models, calling for more balanced and ethical content moderation practices.

Roberto Balestri, Pasquale Cascarano, Mirko Degli Esposti et al.

This paper introduces TRAILDREAMS, a framework that uses a large language model (LLM) to automate the production of movie trailers. The purpose of LLM is to select key visual sequences and impactful dialogues, and to help TRAILDREAMS to generate audio elements such as music and voiceovers. The goal is to produce engaging and visually appealing trailers efficiently. In comparative evaluations, TRAILDREAMS surpasses current state-of-the-art trailer generation methods in viewer ratings. However, it still falls short when compared to real, human-crafted trailers. While TRAILDREAMS demonstrates significant promise and marks an advancement in automated creative processes, further improvements are necessary to bridge the quality gap with traditional trailers.

Roberto Balestri

This paper introduces AI Blob!, an experimental system designed to explore the potential of semantic cataloging and Large Language Models (LLMs) for the retrieval and recontextualization of archival television footage. Drawing methodological inspiration from Italian television programs such as Blob (RAI Tre, 1989-), AI Blob! integrates automatic speech recognition (ASR), semantic embeddings, and retrieval-augmented generation (RAG) to organize and reinterpret archival content. The system processes a curated dataset of 1,547 Italian television videos by transcribing audio, segmenting it into sentence-level units, and embedding these segments into a vector database for semantic querying. Upon user input of a thematic prompt, the LLM generates a range of linguistically and conceptually related queries, guiding the retrieval and recombination of audiovisual fragments. These fragments are algorithmically selected and structured into narrative sequences producing montages that emulate editorial practices of ironic juxtaposition and thematic coherence. By foregrounding dynamic, content-aware retrieval over static metadata schemas, AI Blob! demonstrates how semantic technologies can facilitate new approaches to archival engagement, enabling novel forms of automated narrative construction and cultural analysis. The project contributes to ongoing debates in media historiography and AI-driven archival research, offering both a conceptual framework and a publicly available dataset to support further interdisciplinary experimentation.