http://nlp.unibo.it/tag/local-explanation/Local ExplanationHugo Blox Builder (https://hugoblox.com)en-usMon, 02 Mar 2026 00:00:00 +0000http://nlp.unibo.it/media/icon_hu_7613a4a452ac7087.pnghttp://nlp.unibo.it/tag/local-explanation/http://nlp.unibo.it/proposals_interpretability/extraction/Mon, 02 Mar 2026 00:00:00 +0000http://nlp.unibo.it/proposals_interpretability/extraction/<p><strong>Description:</strong><br> Rationalization is a type of example-specific explanation. However, samples belonging to the same class might share similar rationales. The idea is to define ways to go from a local explanation (i.e., rationalization) to a global explanation (i.e., knowledge base) by aggregating and summarizing extracted rationales. This can be done with LLMs (e.g., prompting techniques) or other solutions.</p> <p><strong>Contact:</strong> <a href="mailto:federico.ruggeri6@unibo.it">Federico Ruggeri</a></p> <p><strong>References:</strong></p> <p><strong>A Game Theoretic Approach to Class-wise Selective Rationalization</strong><br> Shiyu Chang, Yang Zhang, Mo Yu, Tommi S. Jaakkola. 33rd Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, 2019.<br> <a href="https://papers.neurips.cc/paper_files/paper/2019/file/5ad742cd15633b26fdce1b80f7b39f7c-Paper.pdf" target="_blank" rel="noopener">PDF</a></p>