# LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints

arXiv: https://arxiv.org/abs/2410.06458 · HTML: https://mlsanity.com/paper/2410.06458/

## Key facts

- Cited by 35 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 79 of its 101 references that are in the map.
- First posted on arXiv 9 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 79)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [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)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [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)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [Galactica: A Large Language Model for Science](https://mlsanity.com/paper/2211.09085/) (2022)

## Built on by (most cited first, 30 of 35)

- [A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?](https://mlsanity.com/paper/2503.24235/) (2025)
- [SETS: Leveraging Self-Verification and Self-Correction for Improved Test-Time Scaling](https://mlsanity.com/paper/2501.19306/) (2025)
- [Thinking Machines: A Survey of LLM based Reasoning Strategies](https://mlsanity.com/paper/2503.10814/) (2025)
- [RubricEval: A Rubric-Level Meta-Evaluation Benchmark for LLM Judges in Instruction Following](https://mlsanity.com/paper/2603.25133/) (2026)
- [Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models](https://mlsanity.com/paper/2506.01413/) (2025)
- [Lost at the Beginning of Reasoning](https://mlsanity.com/paper/2506.22058/) (2025)
- [Can Language Models Follow Multiple Turns of Entangled Instructions?](https://mlsanity.com/paper/2503.13222/) (2025)
- [FactSelfCheck: Fact-Level Black-Box Hallucination Detection for LLMs](https://mlsanity.com/paper/2503.17229/) (2025)
- [Accelerating Earth Science Discovery via Multi-Agent LLM Systems](https://mlsanity.com/paper/2503.05854/) (2025)
- [MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training](https://mlsanity.com/paper/2502.11541/) (2025)
- [ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection](https://mlsanity.com/paper/2505.16475/) (2025)
- [RECAST: Expanding the Boundaries of LLMs' Complex Instruction Following with Multi-Constraint Data](https://mlsanity.com/paper/2505.19030/) (2025)
- [WildIFEval: Instruction Following in the Wild](https://mlsanity.com/paper/2503.06573/) (2025)
- [Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Ability](https://mlsanity.com/paper/2506.15629/) (2025)
- [Are Checklists Really Useful for Automatic Evaluation of Generative Tasks?](https://mlsanity.com/paper/2508.15218/) (2025)
- [Revisiting the Reliability of Language Models in Instruction-Following](https://mlsanity.com/paper/2512.14754/) (2025)
- [Retrieval-Augmented LLM Agents: Learning to Learn from Experience](https://mlsanity.com/paper/2603.18272/) (2026)
- [Revision or Re-Solving? Decomposing Second-Pass Gains in Multi-LLM Pipelines](https://mlsanity.com/paper/2604.01029/) (2026)
- [Evaluating the Efficacy of LLM-Based Reasoning for Multiobjective HPC Job Scheduling](https://mlsanity.com/paper/2506.02025/) (2025)
- [Same Evidence, Different Answers: Canonical-Context On-Policy Distillation for Multi-Turn Language Models](https://mlsanity.com/paper/2605.30251/) (2026)
- [Critique-Guided Distillation for Robust Reasoning via Refinement](https://mlsanity.com/paper/2505.11628/) (2025)
- [Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky](https://mlsanity.com/paper/2507.03336/) (2025)
- [Self-Review Framework for Enhancing Instruction Following Capability of LLM](https://mlsanity.com/paper/2507.05598/) (2025)
- [CLARIFID: Improving Radiology Report Generation by Reinforcing Clinically Accurate Impressions and Enforcing Detailed Findings](https://mlsanity.com/paper/2507.17234/) (2025)
- [Enhancing LLM Instruction Following: An Evaluation-Driven Multi-Agentic Workflow for Prompt Instructions Optimization](https://mlsanity.com/paper/2601.03359/) (2026)
- [SEIF: Self-Evolving Reinforcement Learning for Instruction Following](https://mlsanity.com/paper/2605.07465/) (2026)
- [When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems](https://mlsanity.com/paper/2605.30102/) (2026)
- [Instruction Stacking Collapse: A Benchmark and the Capability-Dependent Value of Prompt Compilation](https://mlsanity.com/paper/2608.02639/) (2026)
- [Joint Consistency: A Unified Test-Time Aggregation Framework via Energy Minimization](https://mlsanity.com/paper/2605.06219/) (2026)
- [Bridging Auxiliary Constraints to Resolve Instruction Following in Large Reasoning Models](https://mlsanity.com/paper/2606.03624/) (2026)

## Abstract (arXiv)

Instruction following is a key capability for LLMs. However, recent studies have shown that LLMs often struggle with instructions containing multiple constraints (e.g. a request to create a social media post "in a funny tone" with "no hashtag"). Despite this, most evaluations focus solely on synthetic data. To address this, we introduce RealInstruct, the first benchmark designed to evaluate LLMs' ability to follow real-world multi-constrained instructions by leveraging queries real users asked AI assistants. We also investigate model-based evaluation as a cost-effective alternative to human annotation for this task. Our findings reveal that even the proprietary GPT-4 model fails to meet at least one constraint on over 21% of instructions, highlighting the limitations of state-of-the-art models. To address the performance gap between open-source and proprietary models, we propose the Decompose, Critique and Refine (DeCRIM) self-correction pipeline, which enhances LLMs' ability to follow constraints. DeCRIM works by decomposing the original instruction into a list of constraints and using a Critic model to decide when and where the LLM's response needs refinement. Our results show that DeCRIM improves Mistral's performance by 7.3% on RealInstruct and 8.0% on IFEval even with weak feedback. Moreover, we demonstrate that with strong feedback, open-source LLMs with DeCRIM can outperform GPT-4 on both benchmarks.