# Beyond Accuracy Optimization: Computer Vision Losses for Large Language Model Fine-Tuning Source: [Beyond Accuracy Optimization: Computer Vision Losses for Large Language Model Fine-Tuning]() Collection index: [llms.txt]() Data updated: 2025-10-26T03:48:32.506Z Authors: Daniele Rege Cambrin, Giuseppe Gallipoli, Irene Benedetto, Luca Cagliero, Paolo Garza Published: 2024-09-20T16:46:17.000Z ## Abstract Large Language Models (LLMs) have demonstrated impressive performance across various tasks. However, current training approaches combine standard cross-entropy loss with extensive data, human feedback, or ad hoc methods to enhance performance. These solutions are often not scalable or feasible due to their associated costs, complexity, or resource requirements. This study investigates the use of established semantic segmentation loss functions in natural language generation to create a versatile, practical, and scalable solution for fine-tuning different architectures. We evaluate their effectiveness in solving Math Word Problems and question answering across different models of varying sizes. For the analyzed tasks, we found that the traditional Cross-Entropy loss represents a sub-optimal choice, while models trained to minimize alternative (task-dependent) losses, such as Focal or Lov\\'asz, achieve a mean improvement of +42% on exact match without requiring additional data or human feedback. These findings suggest a promising pathway for more efficient and accessible training processes. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()