Mauricio Rivera

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 (accepted)

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

Large Language Models have emerged as prime candidates to tackle misinformation mitigation. However, existing approaches struggle with hallu… (see more)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 (preprint)

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

2024-01-13

ArXiv (preprint)

doi.org