🛰️ Daily AI Frontier
‹ back to 2026-09-22

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

Research Human-AI Verification

Ranking

Overall 85
Content 100
Popularity N/A

No observed public metrics; popularity remains neutral/archived.

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

Merged summary

TL;DR - This paper models human-LLM deliberation as an interactive proof in which a resource-bounded user verifies an LLM’s claims through requested supporting details rather than internal-model transparency. It establishes when such local checks can reliably certify claims and highlights the practical limits imposed by human effort, expertise, and fatigue.

  • Proves anytime-valid soundness against adaptive LLM provers when false-pass and human-error bounds remain valid after every relevant interaction history.
  • Establishes finite-horizon completeness under additional assumptions about honest-response adequacy and sufficient diagnostic progress.
  • Shows that accumulating checks can strengthen acceptance evidence, but each check requires a useful LLM response and reliable human evaluation.
  • Identifies resource regimes where a sequence of local checks is certifiable even though an equivalent global check is not.

Sources (1)

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

arXiv cs.CL Baotong Zhang, Dean Foster, JoĂŁo Sedoc 2026-09-21 arXiv:2609.24895
Public signals N/A
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · N/A X · N/A Fetched 2026-09-26 14:14:45.065486 UTC

TL;DR - This paper models human-LLM deliberation as an interactive proof in which a resource-bounded user verifies an LLM’s claims through requested supporting details rather than internal-model transparency. It establishes when such local checks can reliably certify claims and highlights the practical limits imposed by human effort, expertise, and fatigue.

  • Proves anytime-valid soundness against adaptive LLM provers when false-pass and human-error bounds remain valid after every relevant interaction history.
  • Establishes finite-horizon completeness under additional assumptions about honest-response adequacy and sufficient diagnostic progress.
  • Shows that accumulating checks can strengthen acceptance evidence, but each check requires a useful LLM response and reliable human evaluation.
  • Identifies resource regimes where a sequence of local checks is certifiable even though an equivalent global check is not.
item →