“Finetuning y RAG Asistente Legal Inteligente”
| dc.contributor.advisor | Santa Quintero, Ricardo Andres | |
| dc.contributor.author | Gonzalez Torres, Daniel Leonardo | |
| dc.coverage.spatial | Bogotá | spa |
| dc.creator.email | daniell-gonzalezt@unilibre.edu.co | spa |
| dc.date.accessioned | 2025-06-04T17:14:33Z | |
| dc.date.available | 2025-06-04T17:14:33Z | |
| dc.date.created | 2025-04-07 | |
| dc.description.abstract | El video presenta el desarrollo de un asistente legal inteligente que utiliza el proceso de fine-tuning para adaptar la inteligencia artificial mediante ejemplos específicos de preguntas y respuestas. Se emplean herramientas como Google Colab y la librería Pandas para transformar datos de archivos Excel a un formato adecuado para el fine-tuning, utilizando el modelo GPT-3.5 Turbo por su costo y eficiencia, mientras se considera la posibilidad de modelos más avanzados como GPT-4 en el futuro. Es fundamental establecer un contexto a través de un prompt del sistema para definir la personalidad del asistente y cómo debe responder en un entorno legal. Además, se discute la importancia de evaluar los costos asociados al uso de la API de OpenAI y se sugiere crear asistentes especializados para mejorar la precisión en la atención al usuario. La colaboración entre los equipos de ingeniería y derecho es esencial para asegurar que las soluciones desarrolladas respondan a las necesidades del campo legal. | spa |
| dc.description.abstractenglish | The video presents the development of an intelligent legal assistant that uses fine-tuning to adapt artificial intelligence using specific question and answer examples. Tools such as Google Colab and the Pandas library are used to transform data from Excel files into a format suitable for fine-tuning, using the GPT-3.5 Turbo model for its cost and efficiency, while considering the possibility of more advanced models such as GPT-4 in the future. Establishing context through a system prompt is essential to define the assistant's personality and how it should respond in a legal environment. Additionally, the video discusses the importance of evaluating the costs associated with using the OpenAI API, and suggests creating specialized assistants to improve the accuracy of user support. Collaboration between engineering and legal teams is essential to ensure that the developed solutions meet the needs of the legal field. | spa |
| dc.description.sponsorship | Universidad Libre -- Ingenieria -- Ingenieria de sistemas | spa |
| dc.format | spa | |
| dc.identifier.uri | https://hdl.handle.net/10901/31260 | |
| dc.relation.references | Abacus AI. (2023). Creating AI Agents with Abacus. Retrieved from https://www.abacus.ai/ | spa |
| dc.relation.references | Rauber, J., & Ziemann, T. (2020). Enabling Data-Driven Decisions through AI: A Practical Approach. Information Systems, 95, 101-113. https://doi.org/10.1016/j.is.2020.101113 | spa |
| dc.relation.references | Goh, G., & Wong, H. (2022). The Role of AI in Legal Services: Opportunities and Challenges. Harvard Business Review. https://hbr.org/2022/03/the-role-of-ai-in-legal-services | spa |
| dc.relation.references | Kearns, M., & Neel, S. (2021). A Commentary on Fairness in Machine Learning. Journal of Machine Learning Research, 22(85), 1-23. http://www.jmlr.org/papers/volume22/20-151/20-151.pdf | spa |
| dc.relation.references | Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., ... & Amodei, D. (2020). Language Models are Few-Shot Learners. Advances in Neural Information Processing Systems, 33, 1877-1901. https://arxiv.org/abs/2005.14165 | spa |
| dc.relation.references | Zhang, Y., & Kuo, L. (2021). Fine-Tuning Pre-trained Language Models: Weight Initialization and Dataset Selection. Journal of Language Technology, 12(1), 34-46. https://doi.org/10.1234/jlt.2021.1201 | spa |
| dc.relation.references | Google. (2023). Google Colab Documentation. https://colab.research.google.com/ | spa |
| dc.relation.references | OpenAI. (2023). GPT-3.5 Turbo Documentation. https://platform.openai.com/docs/models/gpt-3-5 | spa |
| dc.relation.references | Pandas Development Team. (2023). Pandas Documentation. https://pandas.pydata.org/docs/ | spa |
| dc.relation.youtube | https://youtu.be/9P_rnvIBOIM?si=d3b8PwMF5k_cSWaL | |
| dc.rights.accessrights | info:eu-repo/semantics/openAccess | spa |
| dc.subject | Fine-tuning | spa |
| dc.subject | Inteligencia Artificial | spa |
| dc.subject | Google Colab | spa |
| dc.subject | Libreria Pandas | spa |
| dc.subject | Formato JSONL | spa |
| dc.subject | GPT 3.5 Turbo | spa |
| dc.subject | GPT 4 | spa |
| dc.subject | Prompt del sistema | spa |
| dc.subject | Personalidad del asistente | spa |
| dc.subject | Precisión | spa |
| dc.subject | API | spa |
| dc.subject | JurisLibreIA | spa |
| dc.subject | Asistentes especializados | spa |
| dc.subject.subjectenglish | Fine-tuning | spa |
| dc.subject.subjectenglish | Artificial Intelligence | spa |
| dc.subject.subjectenglish | Google Colab | spa |
| dc.subject.subjectenglish | Pandas Library | spa |
| dc.subject.subjectenglish | JSONL Format | spa |
| dc.subject.subjectenglish | GPT 3.5 Turbo | spa |
| dc.subject.subjectenglish | GPT 4 | spa |
| dc.subject.subjectenglish | System prompt | spa |
| dc.subject.subjectenglish | Assistant personality | spa |
| dc.subject.subjectenglish | Acuracy | spa |
| dc.subject.subjectenglish | API | spa |
| dc.subject.subjectenglish | JurisLibreIA | spa |
| dc.subject.subjectenglish | Especialized assistants | spa |
| dc.title | “Finetuning y RAG Asistente Legal Inteligente” | spa |
| dc.title.alternative | Conference: “Finetuning and RAG Smart Legal Assistant” | spa |
| dc.type.driver | info:eu-repo/semantics/bachelorThesis | spa |
| dc.type.local | Tesis de Pregrado | spa |
Archivos
Bloque original
1 - 2 de 2
Cargando...
- Nombre:
- Conferencia “Finetuning y RAG Asistente Legal Inteligente”.pdf
- Tamaño:
- 202.71 KB
- Formato:
- Adobe Portable Document Format
- Descripción:
Cargando...
- Nombre:
- Formato autorización PUBLICACIÓN DE OBRAS - Conferencia “Finetuning y RAG Asistente Legal Inteligente”.pdf
- Tamaño:
- 216.91 KB
- Formato:
- Adobe Portable Document Format
- Descripción:
Bloque de licencias
1 - 1 de 1
Cargando...
- Nombre:
- license.txt
- Tamaño:
- 1.71 KB
- Formato:
- Item-specific license agreed upon to submission
- Descripción: