# When Roles Fail: Epistemic Constraints on Advocate Role Fidelity in LLM-Based Political Statement Analysis

arXiv: https://arxiv.org/abs/2604.27228 · HTML: https://mlsanity.com/paper/2604.27228/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 7 of its 60 references that are in the map.
- First posted on arXiv 29 Apr 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 7 of 7)

- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2511.00222/) (2025)
- [Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learning](https://mlsanity.com/paper/2503.17662/) (2025)
- [Generative Adversarial Reviews: When LLMs Become the Critic](https://mlsanity.com/paper/2412.10415/) (2024)
- [Revealing Political Bias in LLMs through Structured Multi-Agent Debate](https://mlsanity.com/paper/2506.11825/) (2025)
- [From Safety Risk to Design Principle: Peer-Preservation in Multi-Agent LLM Systems and Its Implications for Orchestrated Democratic Discourse Analysis](https://mlsanity.com/paper/2604.08465/) (2026)
- [Peer Identity Bias in Multi-Agent LLM Evaluation: An Empirical Study Using the TRUST Democratic Discourse Analysis Pipeline](https://mlsanity.com/paper/2604.22971/) (2026)

## Built on by (most cited first, 2 of 2)

- [Can Multi-Agent LLMs Identify Their Peers? Stylometric Fingerprinting in Role-Constrained Political Analysis](https://mlsanity.com/paper/2606.09854/) (2026)
- [Beyond Acoustic Emotion Recognition: Multimodal Pathos Analysis in Political Speech Using LLM-Based and Acoustic Emotion Models](https://mlsanity.com/paper/2605.22732/) (2026)

## Abstract (arXiv)

Democratic discourse analysis systems increasingly rely on multi-agent LLM pipelines in which distinct evaluator models are assigned adversarial roles to generate structured, multi-perspective assessments of political statements. A core assumption is that models will reliably maintain their assigned roles. This paper provides the first systematic empirical test of that assumption using the TRUST pipeline. We develop an epistemic stance classifier that identifies advocate roles from reasoning text without relying on surface vocabulary, and measure role fidelity across 60 political statements (30 English, 30 German) using four metrics: Role Drift Index (RDI), Expected Drift Distance (EDD), Directional Drift Index (DDI), and Entropy-based Role Stability (ERS). We identify two failure modes - the Epistemic Floor Effect (fact-check results create an absolute lower bound below which the legitimizing role cannot be maintained) and Role-Prior Conflict (training-time knowledge overrides role instructions for factually unambiguous statements) - as manifestations of a single mechanism: Epistemic Role Override (ERO). Model choice significantly affects role fidelity: Mistral Large outperforms Claude Sonnet by 28pp (67% vs. 39%) and exhibits a qualitatively different failure mode - role abandonment without polarity reversal - compared to Claude's active switch to the opposing stance. Role fidelity is language-robust. Fact-check provider choice is not universally neutral: Perplexity significantly reduces Claude's role fidelity on German statements (Delta = -15pp, p = 0.007) while leaving Mistral unaffected. These findings have direct implications for multi-agent LLM validation: a system validated without role fidelity measurement may systematically misrepresent the epistemic diversity it was designed to provide.