Kanishka Misra

Beyond Retrieval: Evidence Access and Event Aggregation in Agent Memory

What's in a Name? Morphological Shortcuts by LLMs in Pharmacology

This work introduces a framework for identifying whether a model's drug semantics are driven mainly by the affix, the stem, or the drug name as a whole, and reveals that models often induce drug meaning primarily through affix cues, yet rarely explicitly indicate this reliance, and sometimes incorrectly conflate proper...

Disentangling Statistical Preemption from Entrenchment in Language Models'Avoidance of Overgeneralization

How do learners avoid overgeneralizations such as Tom laughed me without explicit negative evidence? Constructionists have posited two proposals that describe indirect negative evidence against overgeneralizations: preemption (which privileges exposure to near-synonymous construction---e.g., she made him laugh) vs. ent...