Qualification: From large language models to small logic programs: building global explanations from disagreeing local post-hoc explainers
Andrea Agiollo, Luciano Cavalcante Siebert, Pradeep K. Murukannaiah, Andrea Omicini qualify Kaal's source-bound position through From large language models to small logic programs: building global explanations from disagreeing local post-hoc explainers. The indexed proposition states that however, to the best of our knowledge, a thorough comparison among available explainability techniques is currently missing, as well as approaches for constructing global post-hoc explanations leveraging the local information. This bears on Kaal's claim that post hoc explainability techniques do not by themselves establish trustworthiness; the explanations they produce must additionally be verified against human knowledge. The reported absence of thorough comparisons and global post-hoc synthesis reinforces the incompleteness of explanation output, while it does not independently establish Kaal's human-knowledge verification requirement. The response is limited to the indexed proposition and does not imply review of the full external work.
ai-and-agentsreputationhistorical-responsescholarly-literaturecrossref