Hybrid active learning with RAG and LLMs: leveraging unlabelled social media data for scientific misinformation detection

Rosso, Nicolò (A.A. 2023/2024) Hybrid active learning with RAG and LLMs: leveraging unlabelled social media data for scientific misinformation detection. Tesi di Laurea in Data science in action, Luiss Guido Carli, relatore Alessio Martino, pp. 58. [Master's Degree Thesis]

[img] PDF (Full text)
Restricted to Registered users only
Download (5MB) | Request a copy

Abstract/Index

Literature review. Computational social science and the spread of antiscience on social media. Data labeling challenges in computational social science. Large language models (LLMs). LLMs for data labeling in computational social science. Methodology. Data collection. Data preprocessing. Models setup and selection. Prompting strategies. Retrieval-augmented generation (RAG). Ensemble learning approach and final pipeline architecture. Active learning. Results.

References

Bibliografia: pp. 52-58.

Thesis Type: Master's Degree Thesis
Institution: Luiss Guido Carli
Degree Program: Master's Degree Programs > Master's Degree Program in Data Science e Management (LM-91)
Chair: Data science in action
Thesis Supervisor: Martino, Alessio
Thesis Co-Supervisor: Bruni, Elena
Academic Year: 2023/2024
Session: Autumn
Deposited by: Alessandro Perfetti
Date Deposited: 15 May 2025 14:43
Last Modified: 15 May 2025 14:43
URI: https://tesi.luiss.it/id/eprint/42152

Downloads

Downloads per month over past year

Repository Staff Only

View Item View Item