Antonio Rago

Argumentation semantics could be the key to reliable and explainable debate judgement in AI, outperforming traditional LLM-based methods in formal guarantees.

LLM summaries of parliamentary debates often misrepresent the original arguments, but a new argumentation-based framework can pinpoint exactly where the reasoning goes wrong.

Forget hand-tuning argument base scores – this new method automatically extracts them from user preferences, unlocking more transparent and contestable AI.