# The Deliberative Deficit: An Empirical Critique of LLMs in Democratic Discourse

arXiv: https://arxiv.org/abs/2608.10186 · HTML: https://mlsanity.com/paper/2608.10186/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 49 references that are in the map.
- First posted on arXiv 10 Aug 2026.

## Builds on (most cited first, 18 of 18)

- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Systematic Biases in LLM Simulations of Debates](https://mlsanity.com/paper/2402.04049/) (2024)
- [The Homogenizing Effect of Large Language Models on Human Expression and Thought](https://mlsanity.com/paper/2508.01491/) (2025)
- [Can LLM Agents Really Debate? A Controlled Study of Multi-Agent Debate in Logical Reasoning](https://mlsanity.com/paper/2511.07784/) (2025)
- [The simulation of judgment in LLMs](https://mlsanity.com/paper/2502.04426/) (2025)
- [Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities](https://mlsanity.com/paper/2503.17979/) (2025)
- [Language Agents as Digital Representatives in Collective Decision-Making](https://mlsanity.com/paper/2502.09369/) (2025)
- [Game Reasoning Arena: A Framework and Benchmark for Assessing Reasoning Capabilities of Large Language Models via Game Play](https://mlsanity.com/paper/2508.03368/) (2025)
- [Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces](https://mlsanity.com/paper/2604.08362/) (2026)
- [Can AI Truly Represent Your Voice in Deliberations? A Comprehensive Study of Large-Scale Opinion Aggregation with LLMs](https://mlsanity.com/paper/2510.05154/) (2025)
- [AQuA -- Combining Experts' and Non-Experts' Views To Assess Deliberation Quality in Online Discussions Using LLMs](https://mlsanity.com/paper/2404.02761/) (2024)
- [Decentralising LLM Alignment: A Case for Context, Pluralism, and Participation](https://mlsanity.com/paper/2509.08858/) (2025)
- [Extending RLVR to Open-Ended Tasks via Verifiable Multiple-Choice Reformulation](https://mlsanity.com/paper/2511.02463/) (2025)
- [Beyond the Illusion of Consensus: From Surface Heuristics to Knowledge-Grounded Evaluation in LLM-as-a-Judge](https://mlsanity.com/paper/2603.11027/) (2026)
- [Social Simulations with Large Language Model Risk Utopian Illusion](https://mlsanity.com/paper/2510.21180/) (2025)
- [Does LLM Alignment Really Need Diversity? An Empirical Study of Adapting RLVR Methods for Moral Reasoning](https://mlsanity.com/paper/2603.10588/) (2026)
- [Habermolt: Delegating Deliberation to AI Representatives](https://mlsanity.com/paper/2605.24413/) (2026)

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

- [Measuring AI Accountability Through Argumentation Analysis: Can Model Reasoning Withstand Scrutiny?](https://mlsanity.com/paper/2609.05088/) (2026)
- [From Simulated Citizens to Simulated Deliberation: Challenges in Representation and Interaction](https://mlsanity.com/paper/2609.07573/) (2026)

## Abstract (arXiv)

LLMs are increasingly deployed in settings that require collective reasoning on complex, value-laden problems. Confidence in these deployments rests largely on benchmarks for verifiable tasks (mathematics, coding, coordination games), yet many of these applications concern problems where no objectively correct answer exists and where decision quality instead depends on integrating pluralistic perspectives to find mutually acceptable solutions. We argue that LLM reasoning capacity on this class of problems cannot be fully inferred from verifiable-task benchmarks, and that procedural evaluations of LLM discourse (respectfulness, justification, engagement) are systematically insufficient. We apply the Deliberative Reason Index (DRI), a measure developed in political science and validated across citizen assemblies, as a tool for evaluating reliable group-level reasoning on pluralistic, non-verifiable problems. Synthesizing recent evidence across 1,980 five-agent LLM runs on 12 citizen-assembly topics across 11 frontier model configurations, we find that LLM groups produce discourse with procedural quality comparable to human deliberation, while gains in intersubjective consistency are small, topic-dependent, and concentrated on tractable rather than ethically contested questions. LLM groups exhibit roughly one-third the perspective diversity of human assemblies and reverse the human convergence pattern: human deliberation decreases dispersion as diverse views synthesise, whereas LLM deliberation increases it. Engineering diversity through persona prompting does not restore the human dynamic but inverts which component of deliberative reasoning is updated. Our conclusion is constraining rather than prohibitive: LLMs can function as tools supporting human reasoning on pluralistic problems, but current evidence does not license treating them as autonomous deliberative agents.