Portrait de Mauricio Rivera n'est pas disponible

Mauricio Rivera

mauriv2010@gmail.com
Maîtrise recherche - UdeM
Superviseur⋅e principal⋅e
Marco Bonizzato
Sujets de recherche
Modèles bayésiens
NeuroIA
Optimisation en boîte noire

Publications

Web Retrieval Agents for Evidence-Based Misinformation Detection
Jacob-Junqi Tian
Hao Yu
Yury Orlovskiy
Tyler Vergho
Mauricio Rivera
Mayank Goel
Zachary Yang
Jean-François Godbout
Reihaneh Rabbany
Kellin Pelrine
2024-07-10
colmweb.org/COLM/2024/Conference (accepté)
doi.org
openreview.net
Combining Confidence Elicitation and Sample-based Methods for Uncertainty Quantification in Misinformation Mitigation
Mauricio Rivera
Jean-François Godbout
Reihaneh Rabbany
Kellin Pelrine
2024-01-13
ArXiv (prépublication)
doi.org
arxiv.org
Combining Confidence Elicitation and Sample-based Methods for Uncertainty Quantification in Misinformation Mitigation
Mauricio Rivera
Jean-François Godbout
Reihaneh Rabbany
Kellin Pelrine
Large Language Models have emerged as prime candidates to tackle misinformation mitigation. However, existing approaches struggle with hallu… (voir plus)cinations and overconfident predictions. We propose an uncertainty quantification framework that leverages both direct confidence elicitation and sampled-based consistency methods to provide better calibration for NLP misinformation mitigation solutions. We first investigate the calibration of sample-based consistency methods that exploit distinct features of consistency across sample sizes and stochastic levels. Next, we evaluate the performance and distributional shift of a robust numeric verbalization prompt across single vs. two-step confidence elicitation procedure. We also compare the performance of the same prompt with different versions of GPT and different numerical scales. Finally, we combine the sample-based consistency and verbalized methods to propose a hybrid framework that yields a better uncertainty estimation for GPT models. Overall, our work proposes novel uncertainty quantification methods that will improve the reliability of Large Language Models in misinformation mitigation applications.
2024-01-13
ArXiv (prépublication)
doi.org
arxiv.org