Selective Rationalization

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

Understand whether we can develop a MoE model for selective rationalization to address interlocking.

Evaluate LLM capabilities in performing selective rationalization via prompting

Applying rationalization in these contexts by also enforcing some structural constraints depending on the given scenario of application