Combining Confidence Elicitation and Sample-based Methods for Uncertainty Quantification in Misinformation Mitigation
This work addresses reliability issues in misinformation mitigation using LLMs, though it appears incremental as it builds on existing uncertainty quantification techniques.
The paper tackles the problem of hallucinations and overconfident predictions in Large Language Models for misinformation mitigation by proposing a hybrid uncertainty quantification framework that combines confidence elicitation and sample-based consistency methods, resulting in better calibration for GPT models.
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.