# Universal Self-Consistency for Large Language Model Generation

arXiv: https://arxiv.org/abs/2311.17311 · HTML: https://mlsanity.com/paper/2311.17311/

## Key facts

- Cited by 203 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 42 of its 47 references that are in the map.
- First posted on arXiv 29 Nov 2023.

## 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 42)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [Towards a Human-like Open-Domain Chatbot](https://mlsanity.com/paper/2001.09977/) (2020)
- [Is ChatGPT a Good NLG Evaluator? A Preliminary Study](https://mlsanity.com/paper/2303.04048/) (2023)
- [CodeT: Code Generation with Generated Tests](https://mlsanity.com/paper/2207.10397/) (2022)
- [Towards Expert-Level Medical Question Answering with Large Language Models](https://mlsanity.com/paper/2305.09617/) (2023)
- [Efficient Attentions for Long Document Summarization](https://mlsanity.com/paper/2104.02112/) (2021)
- [Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners](https://mlsanity.com/paper/2307.01928/) (2023)
- [LEVER: Learning to Verify Language-to-Code Generation with Execution](https://mlsanity.com/paper/2302.08468/) (2023)
- [Making Large Language Models Better Reasoners with Step-Aware Verifier](https://mlsanity.com/paper/2206.02336/) (2022)
- [ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding](https://mlsanity.com/paper/2305.14196/) (2023)
- [Progressive-Hint Prompting Improves Reasoning in Large Language Models](https://mlsanity.com/paper/2304.09797/) (2023)

## Built on by (most cited first, 30 of 203)

- [TTRL: Test-Time Reinforcement Learning](https://mlsanity.com/paper/2504.16084/) (2025)
- [When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs](https://mlsanity.com/paper/2406.01297/) (2024)
- [Scalable Best-of-N Selection for Large Language Models via Self-Certainty](https://mlsanity.com/paper/2502.18581/) (2025)
- [Distilling System 2 into System 1](https://mlsanity.com/paper/2407.06023/) (2024)
- [From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models](https://mlsanity.com/paper/2406.16838/) (2024)
- [SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code](https://mlsanity.com/paper/2403.01248/) (2024)
- [To Believe or Not to Believe Your LLM](https://mlsanity.com/paper/2406.02543/) (2024)
- [Approaching Human-Level Forecasting with Language Models](https://mlsanity.com/paper/2402.18563/) (2024)
- [Self-Evaluation Improves Selective Generation in Large Language Models](https://mlsanity.com/paper/2312.09300/) (2023)
- [MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses](https://mlsanity.com/paper/2410.07076/) (2024)
- [SETS: Leveraging Self-Verification and Self-Correction for Improved Test-Time Scaling](https://mlsanity.com/paper/2501.19306/) (2025)
- [Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?](https://mlsanity.com/paper/2502.00674/) (2025)
- [Internal Consistency and Self-Feedback in Large Language Models: A Survey](https://mlsanity.com/paper/2407.14507/) (2024)
- [Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective](https://mlsanity.com/paper/2412.14135/) (2024)
- [Current state of LLM Risks and AI Guardrails](https://mlsanity.com/paper/2406.12934/) (2024)
- [From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging](https://mlsanity.com/paper/2410.01215/) (2024)
- [When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoning](https://mlsanity.com/paper/2504.01005/) (2025)
- [Video-T1: Test-Time Scaling for Video Generation](https://mlsanity.com/paper/2503.18942/) (2025)
- [Calibrating Long-form Generations from Large Language Models](https://mlsanity.com/paper/2402.06544/) (2024)
- [Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use](https://mlsanity.com/paper/2312.04455/) (2023)
- [LLMs Can Generate a Better Answer by Aggregating Their Own Responses](https://mlsanity.com/paper/2503.04104/) (2025)
- [Confidence Calibration and Rationalization for LLMs via Multi-Agent Deliberation](https://mlsanity.com/paper/2404.09127/) (2024)
- [Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order Information](https://mlsanity.com/paper/2510.01499/) (2025)
- [Soft Self-Consistency Improves Language Model Agents](https://mlsanity.com/paper/2402.13212/) (2024)
- [LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs](https://mlsanity.com/paper/2408.08656/) (2024)
- [Watermarking Techniques for Large Language Models: A Survey](https://mlsanity.com/paper/2409.00089/) (2024)
- [A Survey on the Honesty of Large Language Models](https://mlsanity.com/paper/2409.18786/) (2024)
- [In-Context Example Selection via Similarity Search Improves Low-Resource Machine Translation](https://mlsanity.com/paper/2408.00397/) (2024)
- [Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation](https://mlsanity.com/paper/2407.02056/) (2024)
- [The Counterfeit Conundrum: Can Code Language Models Grasp the Nuances of Their Incorrect Generations?](https://mlsanity.com/paper/2402.19475/) (2024)

## Abstract (arXiv)

Self-consistency with chain-of-thought prompting (CoT) has demonstrated remarkable performance gains on various challenging tasks, by utilizing multiple reasoning paths sampled from large language models (LLMs). However, self-consistency relies on the answer extraction process to aggregate multiple solutions, which is not applicable to free-form answers. In this work, we propose Universal Self-Consistency (USC), which leverages LLMs themselves to select the most consistent answer among multiple candidates. We evaluate USC on a variety of benchmarks, including mathematical reasoning, code generation, long-context summarization, and open-ended question answering. On open-ended generation tasks where the original self-consistency method is not applicable, USC effectively utilizes multiple samples and improves the performance. For mathematical reasoning, USC matches the standard self-consistency performance without requiring the answer formats to be similar. Finally, without access to execution results, USC also matches the execution-based voting performance on code generation.