Improved Evidence Extraction and Metrics for Document Inconsistency Detection with LLMs
This work addresses document inconsistency detection for users relying on LLMs, but it is incremental as it builds on existing prompting methods with specific enhancements.
The paper tackles the problem of document inconsistency detection by improving evidence extraction capabilities of LLMs, introducing new metrics and a redact-and-retry framework that achieves substantial performance gains over other prompting methods, supported by strong experimental results and a new semi-synthetic dataset.
Large language models (LLMs) are becoming useful in many domains due to their impressive abilities that arise from large training datasets and large model sizes. However, research on LLM-based approaches to document inconsistency detection is relatively limited. We address this gap by investigating evidence extraction capabilties of LLMs for document inconsistency detection. To this end, we introduce new comprehensive evidence-extraction metrics and a redact-and-retry framework with constrained filtering that substantially improves evidence extraction performance over other prompting methods. We support our approach with strong experimental results and release a new semi-synthetic dataset for evaluating evidence extraction.