# N-Critics: Self-Refinement of Large Language Models with Ensemble of Critics

arXiv: https://arxiv.org/abs/2310.18679 · HTML: https://mlsanity.com/paper/2310.18679/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 41 references that are in the map.
- First posted on arXiv 28 Oct 2023.

## Builds on (most cited first, 23 of 23)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [AmbigQA: Answering Ambiguous Open-domain Questions](https://mlsanity.com/paper/2004.10645/) (2020)
- [Toxicity in ChatGPT: Analyzing Persona-assigned Language Models](https://mlsanity.com/paper/2304.05335/) (2023)
- [Generating Sequences by Learning to Self-Correct](https://mlsanity.com/paper/2211.00053/) (2022)
- [Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies](https://mlsanity.com/paper/2308.03188/) (2023)
- [Quark: Controllable Text Generation with Reinforced Unlearning](https://mlsanity.com/paper/2205.13636/) (2022)
- [REFINER: Reasoning Feedback on Intermediate Representations](https://mlsanity.com/paper/2304.01904/) (2023)
- [Read, Revise, Repeat: A System Demonstration for Human-in-the-loop Iterative Text Revision](https://mlsanity.com/paper/2204.03685/) (2022)
- [Deep Reinforcement Learning with Distributional Semantic Rewards for Abstractive Summarization](https://mlsanity.com/paper/1909.00141/) (2019)
- [BERTTune: Fine-Tuning Neural Machine Translation with BERTScore](https://mlsanity.com/paper/2106.02208/) (2021)
- [RTDK-BO: High Dimensional Bayesian Optimization with Reinforced Transformer Deep kernels](https://mlsanity.com/paper/2310.03912/) (2023)
- [Skip Training for Multi-Agent Reinforcement Learning Controller for Industrial Wave Energy Converters](https://mlsanity.com/paper/2209.05656/) (2022)
- [SESCORE2: Learning Text Generation Evaluation via Synthesizing Realistic Mistakes](https://mlsanity.com/paper/2212.09305/) (2022)

## Built on by (most cited first, 8 of 8)

- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [Lifelong Learning of Large Language Model based Agents: A Roadmap](https://mlsanity.com/paper/2501.07278/) (2025)
- [Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in Large Language Models](https://mlsanity.com/paper/2507.02778/) (2025)
- [Understanding the Effects of Iterative Prompting on Truthfulness](https://mlsanity.com/paper/2402.06625/) (2024)
- [What's Wrong? Refining Meeting Summaries with LLM Feedback](https://mlsanity.com/paper/2407.11919/) (2024)
- [Learning Together to Perform Better: Teaching Small-Scale LLMs to Collaborate via Preferential Rationale Tuning](https://mlsanity.com/paper/2506.02519/) (2025)
- [It Helps to Take a Second Opinion: Teaching Smaller LLMs to Deliberate Mutually via Selective Rationale Optimisation](https://mlsanity.com/paper/2503.02463/) (2025)
- [A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content](https://mlsanity.com/paper/2504.16120/) (2025)

## Abstract (arXiv)

We propose a self-correction mechanism for Large Language Models (LLMs) to mitigate issues such as toxicity and fact hallucination. This method involves refining model outputs through an ensemble of critics and the model's own feedback. Drawing inspiration from human behavior, we explore whether LLMs can emulate the self-correction process observed in humans who often engage in self-reflection and seek input from others to refine their understanding of complex topics. Our approach is model-agnostic and can be applied across various domains to enhance trustworthiness by addressing fairness, bias, and robustness concerns. We consistently observe performance improvements in LLMs for reducing toxicity and correcting factual errors.