# Mirror-Consistency: Harnessing Inconsistency in Majority Voting

arXiv: https://arxiv.org/abs/2410.10857 · HTML: https://mlsanity.com/paper/2410.10857/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 35 of its 50 references that are in the map.
- First posted on arXiv 7 Oct 2024.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 30 of 35)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [Are NLP Models really able to Solve Simple Math Word Problems?](https://mlsanity.com/paper/2103.07191/) (2021)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models](https://mlsanity.com/paper/2303.04671/) (2023)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [Language Models can Solve Computer Tasks](https://mlsanity.com/paper/2303.17491/) (2023)
- [Calibration of Pre-trained Transformers](https://mlsanity.com/paper/2003.07892/) (2020)
- [Faithful Chain-of-Thought Reasoning](https://mlsanity.com/paper/2301.13379/) (2023)
- [Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies](https://mlsanity.com/paper/2308.03188/) (2023)
- [Reducing conversational agents' overconfidence through linguistic calibration](https://mlsanity.com/paper/2012.14983/) (2020)
- [REFINER: Reasoning Feedback on Intermediate Representations](https://mlsanity.com/paper/2304.01904/) (2023)
- [SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning](https://mlsanity.com/paper/2308.00436/) (2023)
- [GPT-4 Doesn't Know It's Wrong: An Analysis of Iterative Prompting for Reasoning Problems](https://mlsanity.com/paper/2310.12397/) (2023)
- [Answering Questions by Meta-Reasoning over Multiple Chains of Thought](https://mlsanity.com/paper/2304.13007/) (2023)
- [LLMs cannot find reasoning errors, but can correct them given the error location](https://mlsanity.com/paper/2311.08516/) (2023)
- [Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow](https://mlsanity.com/paper/2306.07209/) (2023)

## Built on by (most cited first, 17 of 17)

- [The Majority is not always right: RL training for solution aggregation](https://mlsanity.com/paper/2509.06870/) (2025)
- [Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO](https://mlsanity.com/paper/2505.11595/) (2025)
- [Beyond Consensus: Mitigating the Agreeableness Bias in LLM Judge Evaluations](https://mlsanity.com/paper/2510.11822/) (2025)
- [ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QA](https://mlsanity.com/paper/2503.06951/) (2025)
- [What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time](https://mlsanity.com/paper/2603.19880/) (2026)
- [Temporal Consistency for LLM Reasoning Process Error Identification](https://mlsanity.com/paper/2503.14495/) (2025)
- [Self-Harmony: Learning to Harmonize Self-Supervision and Self-Play in Test-Time Reinforcement Learning](https://mlsanity.com/paper/2511.01191/) (2025)
- [Optimal Self-Consistency for Efficient Reasoning with Large Language Models](https://mlsanity.com/paper/2511.12309/) (2025)
- [Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning](https://mlsanity.com/paper/2512.02874/) (2025)
- [Beyond Consensus: Trace-Level Synthesis in Mixture of Agents](https://mlsanity.com/paper/2605.29116/) (2026)
- [Multi-chain Graph Refinement and Selection for Reliable Reasoning in Large Language Models](https://mlsanity.com/paper/2511.23136/) (2025)
- [CascadeMind at SemEval-2026 Task 4: A Hybrid Neuro-Symbolic Cascade for Narrative Similarity](https://mlsanity.com/paper/2601.19931/) (2026)
- [GradeSQL: Test-Time Inference with Outcome Reward Models for Text-to-SQL Generation from Large Language Models](https://mlsanity.com/paper/2509.01308/) (2025)
- [Discovering Novel LLM Experts via Task-Capability Coevolution](https://mlsanity.com/paper/2604.14969/) (2026)
- [Neuro-Symbolic AI for LEED compliance: Document-Centric Benchmarking, Deterministic Numeric Checking, and When Multimodal Hurts](https://mlsanity.com/paper/2607.15647/) (2026)
- [Test-Time Augmentation for LLMs: When Input Diversity Beats Output Diversity at Matched Compute](https://mlsanity.com/paper/2608.09351/) (2026)
- [Is This Your Final Answer? Cross-Contextual Consistency as a Measure of LLM Credibility](https://mlsanity.com/paper/2608.10315/) (2026)

## Abstract (arXiv)

Self-Consistency, a widely-used decoding strategy, significantly boosts the reasoning capabilities of Large Language Models (LLMs). However, it depends on the plurality voting rule, which focuses on the most frequent answer while overlooking all other minority responses. These inconsistent minority views often illuminate areas of uncertainty within the model's generation process. To address this limitation, we present Mirror-Consistency, an enhancement of the standard Self-Consistency approach. Our method incorporates a 'reflective mirror' into the self-ensemble decoding process and enables LLMs to critically examine inconsistencies among multiple generations. Additionally, just as humans use the mirror to better understand themselves, we propose using Mirror-Consistency to enhance the sample-based confidence calibration methods, which helps to mitigate issues of overconfidence. Our experimental results demonstrate that Mirror-Consistency yields superior performance in both reasoning accuracy and confidence calibration compared to Self-Consistency.