# Consensus is Not Verification: Why Crowd Wisdom Strategies Fail for LLM Truthfulness

arXiv: https://arxiv.org/abs/2603.06612 · HTML: https://mlsanity.com/paper/2603.06612/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 31 references that are in the map.
- First posted on arXiv 20 Feb 2026.

## Builds on (most cited first, 19 of 19)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback](https://mlsanity.com/paper/2305.14975/) (2023)
- [Taming Overconfidence in LLMs: Reward Calibration in RLHF](https://mlsanity.com/paper/2410.09724/) (2024)
- [Best-of-N Jailbreaking](https://mlsanity.com/paper/2412.03556/) (2024)
- [Great Models Think Alike and this Undermines AI Oversight](https://mlsanity.com/paper/2502.04313/) (2025)
- [Correlated Errors in Large Language Models](https://mlsanity.com/paper/2506.07962/) (2025)
- [How Do Large Language Monkeys Get Their Power (Laws)?](https://mlsanity.com/paper/2502.17578/) (2025)

## Built on by (most cited first, 9 of 9)

- [The Ringelmann Effect in Multi-Agent LLM Systems: A Scaling Law for Effective Team Size](https://mlsanity.com/paper/2606.02646/) (2026)
- [The Honest Quorum Problem: Epistemic Byzantine Fault Tolerance for Agentic Infrastructure](https://mlsanity.com/paper/2607.16109/) (2026)
- [Floor, Ceiling, and the Fusion Gap: How Much of Crowd Reading Attention Can Machines Predict?](https://mlsanity.com/paper/2608.01704/) (2026)
- [When AI Agents Disagree Like Humans: Reasoning Trace Analysis for Human-AI Collaborative Moderation](https://mlsanity.com/paper/2604.03796/) (2026)
- [Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery](https://mlsanity.com/paper/2604.19049/) (2026)
- [Consensus is Strategically Insufficient: Reasoning-Trace Disagreement as a Knowledge-Representation Signal](https://mlsanity.com/paper/2606.04223/) (2026)
- [Statistically Supported LLM Ingredient and Recipe Data Collection in Computational Nutrition](https://mlsanity.com/paper/2607.23273/) (2026)
- [Mitigating LLM sycophancy with RL-based fine-tuning: Bayesian Truth Serum approach](https://mlsanity.com/paper/2608.25267/) (2026)
- [Verification Pulses and the Cost of Escaping Wrong Consensus](https://mlsanity.com/paper/2610.00256/) (2026)

## Abstract (arXiv)

Pass@k and other methods of scaling inference compute can improve language model performance in domains with external verifiers, including mathematics and code, where incorrect candidates can be filtered reliably. This raises a natural question: can we similarly scale compute to elicit gains in truthfulness for domains without convenient verification? We show that across five benchmarks and models, surprisingly, it cannot. Even at 25x the inference cost of naive sampling, polling-style aggregation yields no consistent accuracy gains over single-sample baselines and often amplifies shared misconceptions. We find that under uncertainty, models are better at predicting what other models will say within model ensembles than at identifying what is true, revealing a separation between social prediction and truth verification. Across models and benchmarks, aggregation fails to provide a robust truth signal because language model errors are strongly correlated. The source of correlation goes beyond any individual benchmark: we show that even when conditioned on out of distribution random strings and asked to produce pseudo-random outputs, different models produce correlated outputs. Confidence-based weighting provides no benefit because self-reported confidence fails to reliably distinguish correct from incorrect answers. These results delineate a boundary for inference-time scaling: in verified domains, additional samples provide more candidates for a verifier to filter; in unverified domains, additional samples merely reinforce shared misconceptions.