Author

João Sedoc

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Preprint Sep 2026

Human-LLM Deliberation as Interactive Proof: Conditions for Verifiability Without Transparency

When an LLM supplies an argument that a user could not readily construct, how can the user decide whether to accept its claim? Inspired by interactive proofs, we model human-LLM deliberation as an interaction between a prover with unrestricted internal search and a resource-bounded human verifier. The verifier requests...

Bao-Tong Zhang, D. Foster, João Sedoc · 0 citations

#artificial intelligence Preprint Sep 2026

Epistemic Warrant for LLM Recommendations: Characterizing the Basis for Reliance When Ground Truth Is Unavailable

This work introduces epistemic warrant, a decision-level construct that characterizes the stability of a model's preference and the scope over which that preference holds, and demonstrates that epistemic warrant provides information distinct from verbalized confidence and is not readily explained by decision difficulty...

Shai Vardi, João Sedoc · 0 citations