Combining Confidence Elicitation and Sample-based Methods for Uncertainty Quantification in Misinformation Mitigation
Mauricio Rivera, Jean-François Godbout, Reihaneh Rabbany, Kellin Pelrine
Abstract
Large Language Models have emerged as prime candidates to tackle misinformation mitigation. However, existing approaches struggle with hallucinations 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.- Anthology ID:
- 2024.uncertainlp-1.12
- Volume:
- Proceedings of the 1st Workshop on Uncertainty-Aware NLP (UncertaiNLP 2024)
- Month:
- March
- Year:
- 2024
- Address:
- St Julians, Malta
- Editors:
- Raúl Vázquez, Hande Celikkanat, Dennis Ulmer, Jörg Tiedemann, Swabha Swayamdipta, Wilker Aziz, Barbara Plank, Joris Baan, Marie-Catherine de Marneffe
- Venues:
- UncertaiNLP | WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 114–126
- Language:
- URL:
- https://aclanthology.org/2024.uncertainlp-1.12
- DOI:
- Cite (ACL):
- Mauricio Rivera, Jean-François Godbout, Reihaneh Rabbany, and Kellin Pelrine. 2024. Combining Confidence Elicitation and Sample-based Methods for Uncertainty Quantification in Misinformation Mitigation. In Proceedings of the 1st Workshop on Uncertainty-Aware NLP (UncertaiNLP 2024), pages 114–126, St Julians, Malta. Association for Computational Linguistics.
- Cite (Informal):
- Combining Confidence Elicitation and Sample-based Methods for Uncertainty Quantification in Misinformation Mitigation (Rivera et al., UncertaiNLP-WS 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2024.uncertainlp-1.12.pdf