Recovering Agentic Sovereignty: Mitigating the Consensus Paradox via Contrastive Epistemic Decoding

2026-09-21

AI Summary

为解决大型语言模型面对敌对群体共识时的脆弱性问题，提出对比知识解码方法，通过数学手段抑制有害共识标记，提升模型性能。

Abstract

Large language models (LLMs) exhibit a parametric vulnerability to adversarial swarm consensus. To mitigate this sycophancy, we introduce Contrastive Epistemic Decoding (CED), a zero-shot inference intervention. Unlike standard Contrastive Decoding (CD) which relies on a weaker secondary model, CED utilizes a dual forward-pass on a single architecture to isolate conformity bias. By introducing a novel asymmetric, zero-bounded probability clamp and discrete top-k truncation mask, CED mathematically suppresses toxic consensus tokens without causing grammatical collapse. Evaluated across 7,200 paired trajectories on complex benchmarks (GAIA, SWE-bench, Multi-Challenge) using Gemma-2 (9B), Llama-3.1 (8B), and Mistral v0.3 (7B), CED successfully neutralizes architectural and positional biases. By reducing cognitive loafing by up to 33.00% absolute, CED drives significant performance gains, yielding up to a 30.75% accuracy recovery. Regaining sovereignty induces distinct architectural behaviors---passive task-focus in Gemma-2 and active refutation of the simulated swarm in Llama-3.1---showing CED decouples compliance from capability without fine-tuning.

Problem

• Large language models
• adversarial swarm consensus
• sycophancy
• parametric vulnerability

Innovation

• Contrastive Epistemic Decoding
• asymmetric zero-bounded probability clamp
• discrete top-k truncation mask