Tractable Asymmetric Verification for Large Language Models via Deterministic Replicability
This addresses the problem of computational trust in dynamic LLM systems for AI developers and users, though it is incremental as it builds on existing autoregressive model properties.
The paper tackles the challenge of verifying that LLM outputs in multi-agent systems are genuinely produced by claimed models rather than falsified, proposing a verification framework based on deterministic replicability that enables probabilistic auditing of small output segments. Simulations showed targeted verification can be over 12 times faster than full regeneration with tunable detection probability.
The landscape of Large Language Models (LLMs) shifts rapidly towards dynamic, multi-agent systems. This introduces a fundamental challenge in establishing computational trust, specifically how one agent can verify that another's output was genuinely produced by a claimed LLM, and not falsified or generated by a cheaper or inferior model. To address this challenge, this paper proposes a verification framework that achieves tractable asymmetric effort, where the cost to verify a computation is substantially lower than the cost to perform it. Our approach is built upon the principle of deterministic replicability, a property inherent to autoregressive models that strictly necessitates a computationally homogeneous environment where all agents operate on identical hardware and software stacks. Within this defined context, our framework enables multiple validators to probabilistically audit small, random segments of an LLM's output and it distributes the verification workload effectively. The simulations demonstrated that targeted verification can be over 12 times faster than full regeneration, with tunable parameters to adjust the detection probability. By establishing a tractable mechanism for auditable LLM systems, our work offers a foundational layer for responsible AI and serves as a cornerstone for future research into the more complex, heterogeneous multi-agent systems.