Theme of inquiry

How do modularity, routing, and search affect architecture efficiency?

A question within its area, explored through 5 lines of inquiry below — each a family of specific questions the research asks.


Do accurate-looking LLM outputs hide structural failures in learning and reasoning?

26 specific questions

See all 26 questions in this line of inquiry
What critical LLM failures do standard benchmarks hide?

34 specific questions

See all 34 questions in this line of inquiry
Do language models perform faithful symbolic reasoning independent of semantic grounding?

40 specific questions

See all 40 questions in this line of inquiry
How should we design LLM systems to maintain alignment and control?

17 specific questions

See all 17 questions in this line of inquiry
How do language models inherit human biases from training data?

47 specific questions

See all 47 questions in this line of inquiry