eXplainable Bayesian Multi-Perspective Generative Retrieval
This addresses interpretability and uncertainty issues in retrieval systems for applications like QA and fact-checking, though it appears incremental as it combines existing methods.
The paper tackles the lack of interpretability and overconfident predictions in deterministic retrieval pipelines by integrating Bayesian uncertainty calibration and multi-perspective retrieval with explanation techniques like LIME and SHAP. The result shows substantial performance improvements across three KILT datasets for Question Answering and Fact Checking tasks.
Modern deterministic retrieval pipelines prioritize achieving state-of-the-art performance but often lack interpretability in decision-making. These models face challenges in assessing uncertainty, leading to overconfident predictions. To overcome these limitations, we integrate uncertainty calibration and interpretability into a retrieval pipeline. Specifically, we introduce Bayesian methodologies and multi-perspective retrieval to calibrate uncertainty within a retrieval pipeline. We incorporate techniques such as LIME and SHAP to analyze the behavior of a black-box reranker model. The importance scores derived from these explanation methodologies serve as supplementary relevance scores to enhance the base reranker model. We evaluate the resulting performance enhancements achieved through uncertainty calibration and interpretable reranking on Question Answering and Fact Checking tasks. Our methods demonstrate substantial performance improvements across three KILT datasets.