http://nlp.unibo.it/tag/prompting/PromptingHugo 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/prompting/http://nlp.unibo.it/proposals_interpretability/llms/Mon, 02 Mar 2026 00:00:00 +0000http://nlp.unibo.it/proposals_interpretability/llms/<p><strong>Description:</strong><br> LLMs are ubiquitous in NLP. Our aim is to evaluate LLM capabilities in performing selective rationalization via prompting. How do they compare w.r.t. traditional SPP models?</p> <p><strong>Contact:</strong> <a href="mailto:federico.ruggeri6@unibo.it">Federico Ruggeri</a></p> <p><strong>References:</strong></p> <p><strong>Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery</strong><br> Linan Yue, Qi Liu, Yichao Du, Li Wang, Weibo Gao, Yanqing An.<br> The Twelfth International Conference on Learning Representations, 2024.<br> <a href="https://openreview.net/pdf?id=uGtfk2OphU" target="_blank" rel="noopener">PDF</a></p> <p><strong>Learning Robust Rationales for Model Explainability: A Guidance-Based Approach</strong><br> S Hu, K Yu.<br> Proceedings of the AAAI Conference on Artificial Intelligence, 2024.<br> <a href="https://doi.org/10.1609/aaai.v38i16.29783" target="_blank" rel="noopener">DOI</a> | <a href="https://ojs.aaai.org/index.php/AAAI/article/view/29783/31352" target="_blank" rel="noopener">PDF</a></p>