Recovering Agentic Sovereignty: Mitigating the Consensus Paradox via Contrastive Epistemic Decoding
cs.AI
Submitted: 2026-09-22
Updated: 2026-09-22
License: http://creativecommons.org/licenses/by/4.0/
The gist: Large language models (LLMs) exhibit a parametric vulnerability to adversarial swarm consensus.
Terminology
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.
Sources
- The Llama 3 Herd of Models
- Mistral 7B
- Gemma 2: Improving Open Language Models at a Practical Size
- Beyond the Attention Stability Boundary: Agentic Self-Synthesizing Reasoning Protocols
- The Bystander Effect in Multi-Agent Reasoning: Quantifying Cognitive Loafing in Collaborative Interactions
- The Inverse-Wisdom Law: Architectural Tribalism and the Consensus Paradox in Agentic Swarms
- Simple synthetic data reduces sycophancy in large language models
- Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry
- Representation Engineering: A Top-Down Approach to AI Transparency
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection