# Can AI Truly Represent Your Voice in Deliberations? A Comprehensive Study of Large-Scale Opinion Aggregation with LLMs

arXiv: https://arxiv.org/abs/2510.05154 · HTML: https://mlsanity.com/paper/2510.05154/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 39 references that are in the map.
- First posted on arXiv 2 Oct 2025.

## Builds on (most cited first, 24 of 24)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge](https://mlsanity.com/paper/2410.02736/) (2024)
- [Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges](https://mlsanity.com/paper/2406.12624/) (2024)
- [Fine-tuning language models to find agreement among humans with diverse preferences](https://mlsanity.com/paper/2211.15006/) (2022)
- [Limitations of the LLM-as-a-Judge Approach for Evaluating LLM Outputs in Expert Knowledge Tasks](https://mlsanity.com/paper/2410.20266/) (2024)
- [An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4](https://mlsanity.com/paper/2403.02839/) (2024)
- [A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications](https://mlsanity.com/paper/2503.07137/) (2025)
- [POTATO: The Portable Text Annotation Tool](https://mlsanity.com/paper/2212.08620/) (2022)
- [No Free Labels: Limitations of LLM-as-a-Judge Without Human Grounding](https://mlsanity.com/paper/2503.05061/) (2025)
- [Generative Social Choice](https://mlsanity.com/paper/2309.01291/) (2023)
- [Opportunities and Risks of LLMs for Scalable Deliberation with Polis](https://mlsanity.com/paper/2306.11932/) (2023)
- [Densing Law of LLMs](https://mlsanity.com/paper/2412.04315/) (2024)
- [Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements](https://mlsanity.com/paper/2502.12904/) (2025)
- [One-Shot Labeling for Automatic Relevance Estimation](https://mlsanity.com/paper/2302.11266/) (2023)
- [NeuS: Neutral Multi-News Summarization for Mitigating Framing Bias](https://mlsanity.com/paper/2204.04902/) (2022)
- [Political-LLM: Large Language Models in Political Science](https://mlsanity.com/paper/2412.06864/) (2024)
- [Is Your LLM-Based Multi-Agent a Reliable Real-World Planner? Exploring Fraud Detection in Travel Planning](https://mlsanity.com/paper/2505.16557/) (2025)
- [When Neutral Summaries are not that Neutral: Quantifying Political Neutrality in LLM-Generated News Summaries](https://mlsanity.com/paper/2410.09978/) (2024)

## Built on by (most cited first, 6 of 6)

- [Multi-User Large Language Model Agents](https://mlsanity.com/paper/2604.08567/) (2026)
- [The Deliberative Deficit: An Empirical Critique of LLMs in Democratic Discourse](https://mlsanity.com/paper/2608.10186/) (2026)
- [ProACT: Towards Breakdown-Aware Proactive Agent in Multi-User Collaboration](https://mlsanity.com/paper/2607.03730/) (2026)
- [Humanly: A Configurable and Traceable Environment for Human-AI Collaborative Writing](https://mlsanity.com/paper/2607.21758/) (2026)
- [Toward Collective-Centric Evaluation of Preference Inference for Participatory Democracy](https://mlsanity.com/paper/2609.02990/) (2026)
- [AI Should Facilitate Democratic Deliberation at Scale](https://mlsanity.com/paper/2609.20059/) (2026)

## Abstract (arXiv)

Large-scale public deliberations generate thousands of free-form contributions that must be synthesized into representative and neutral summaries for policy use. While LLMs have been shown as a promising tool to generate summaries for large-scale deliberations, they also risk underrepresenting minority perspectives and exhibiting bias with respect to the input order, raising fairness concerns in high-stakes contexts. Studying and fixing these issues requires a comprehensive evaluation at a large scale, yet current practice often relies on LLMs as judges, which show weak alignment with human judgments. To address this, we present DeliberationBank, a large-scale human-grounded dataset with (1) opinion data spanning ten deliberation questions created by 3,000 participants and (2) summary judgment data annotated by 4,500 participants across four dimensions (representativeness, informativeness, neutrality, policy approval). Using these datasets, we train DeliberationJudge, a fine-tuned DeBERTa model that can rate deliberation summaries from individual perspectives. DeliberationJudge is more efficient and more aligned with human judgements compared to a wide range of LLM judges. With DeliberationJudge, we evaluate 18 LLMs and reveal persistent weaknesses in deliberation summarization, especially underrepresentation of minority positions. Our framework provides a scalable and reliable way to evaluate deliberation summarization, helping ensure AI systems are more representative and equitable for policymaking.