Listed on GrantGunner. Last checked 14 Nov 2026.
About this grant
The project aims to develop novel theoretical frameworks for LLM security, mechanistic interpretability methods, and evaluation protocols to mitigate false information attacks on LLMs. The postdoc will characterize the spectrum of false information used by LLMs at different stages of their life cycle, in order to develop mitigation methods. Research is at the intersection of Natural Language Processing, LLM Security, and Explainable AI.
Who can apply
Applicants should hold a PhD degree or equivalent in Computer Science or a related field, with good written and oral English skills; ideal candidate has educational background, prior research or work experience on Natural Language Processing, LLM Security, and/or Explainable AI.