Lucrări și publicații

This paper surveys the current landscape of poetry generation using large language models, examining both the technical capabilities and the aesthetic limitations of these systems. Through a series of experiments comparing LLM-generated verse with human-authored poetry across multiple dimensions (metaphor density, sonic patterning, emotional resonance), we investigate the boundaries of machine creativity and propose new evaluation frameworks for computational poetry.

We explore the conceptual territory between machine learning loss functions and the poetic tradition of elegy. Both seek to minimize a distance: the loss function between prediction and ground truth, the elegy between presence and absence. This interdisciplinary study draws on computational theory, philosophy of mind, and literary criticism to investigate whether artificial systems can model, if not experience, the structure of grief.

This paper examines the structural parallels between transformer-based attention mechanisms and the cognitive processes underlying poetic attention. We argue that the multi-headed attention paradigm offers a computational metaphor for how poets simultaneously attend to sound, meaning, and form. Through analysis of both neural network architectures and close readings of contemporary poetry, we propose a framework for understanding creative attention as a form of weighted relevance.