Natalie Shapira is a postdoctoral researcher at Northeastern Khoury College of Computer Sciences at Prof. David Bau’s lab, Interpretation of Deep Networks. In her PhD, she combined natural language processing, deep learning and clinical psychology. With over ten years in the industry, she most recently worked as a researcher at Amazon Science. Before that, she held a research position at IBM's research labs, where she served on the Patent Committee. Natalie also has entrepreneurial experience as a co-founder and CSO in projects funded by the Israel Innovation Authority.

I am open to various forms:

• A research proposal that we craft together under a common research interest (see below)

• Join an existing project (led by another researcher or me; ask me directly for current running projects and potential matches)

• Leading a project from the pool of open research questions listed here.

Mechanistic Interpretability: Causal Mediation Analyses, Circuit Discovery

Theory of Mind (ToM): Evaluations, New tests, Multi-modal, Human vs. Machines, Multi Agents

Alignment: LLMs’ Psychology, e.g., anxiety, depression, etc. LLMs’ self ToM, e.g., goals, values, beliefs, etc., LLMs’ perception of others, e.g., entity tracking, belief tracking, privacy, etc., Kindness

While I have no expertise (yet!), I’m also interested in reinforcement learning and the objective function

A good match would be someone who has a strong sense of agency, i.e., a desire and responsibility to lead to whatever success means. They are independent, managing technical issues, familiar with existing methods and tools, and interested in developing the research soft skills and critical thinking. They have a high tolerance for criticism.