# Can Large Language Models Understand Real-World Complex Instructions?

arXiv: https://arxiv.org/abs/2309.09150 · HTML: https://mlsanity.com/paper/2309.09150/

## Key facts

- Cited by 69 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 53 references that are in the map.
- First posted on arXiv 17 Sep 2023.

## Builds on (most cited first, 30 of 34)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [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)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [GLM-130B: An Open Bilingual Pre-trained Model](https://mlsanity.com/paper/2210.02414/) (2022)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models](https://mlsanity.com/paper/2304.06364/) (2023)
- [C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models](https://mlsanity.com/paper/2305.08322/) (2023)
- [How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection](https://mlsanity.com/paper/2301.07597/) (2023)
- [Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor](https://mlsanity.com/paper/2212.09689/) (2022)
- [Orca: Progressive Learning from Complex Explanation Traces of GPT-4](https://mlsanity.com/paper/2306.02707/) (2023)
- [Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents](https://mlsanity.com/paper/2304.09542/) (2023)
- [HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models](https://mlsanity.com/paper/2305.11747/) (2023)
- [Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca](https://mlsanity.com/paper/2304.08177/) (2023)
- [L-Eval: Instituting Standardized Evaluation for Long Context Language Models](https://mlsanity.com/paper/2307.11088/) (2023)
- [Controlled Text Generation with Natural Language Instructions](https://mlsanity.com/paper/2304.14293/) (2023)
- [KoLA: Carefully Benchmarking World Knowledge of Large Language Models](https://mlsanity.com/paper/2306.09296/) (2023)
- [COLLIE: Systematic Construction of Constrained Text Generation Tasks](https://mlsanity.com/paper/2307.08689/) (2023)
- [INSTRUCTEVAL: Towards Holistic Evaluation of Instruction-Tuned Large Language Models](https://mlsanity.com/paper/2306.04757/) (2023)

## Built on by (most cited first, 30 of 69)

- [Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs](https://mlsanity.com/paper/2402.03927/) (2024)
- [Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges](https://mlsanity.com/paper/2406.12624/) (2024)
- [Can LLM-Generated Misinformation Be Detected?](https://mlsanity.com/paper/2309.13788/) (2023)
- [Benchmarking Complex Instruction-Following with Multiple Constraints Composition](https://mlsanity.com/paper/2407.03978/) (2024)
- [Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following](https://mlsanity.com/paper/2410.15553/) (2024)
- [Fake News in Sheep's Clothing: Robust Fake News Detection Against LLM-Empowered Style Attacks](https://mlsanity.com/paper/2310.10830/) (2023)
- [CFBench: A Comprehensive Constraints-Following Benchmark for LLMs](https://mlsanity.com/paper/2408.01122/) (2024)
- [Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems](https://mlsanity.com/paper/2502.19328/) (2025)
- [AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios](https://mlsanity.com/paper/2505.16944/) (2025)
- [LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints](https://mlsanity.com/paper/2410.06458/) (2024)
- [A Comprehensive Evaluation of Cognitive Biases in LLMs](https://mlsanity.com/paper/2410.15413/) (2024)
- [LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarios](https://mlsanity.com/paper/2411.07037/) (2024)
- [IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization](https://mlsanity.com/paper/2411.06208/) (2024)
- [StructFlowBench: A Structured Flow Benchmark for Multi-turn Instruction Following](https://mlsanity.com/paper/2502.14494/) (2025)
- [SysBench: Can Large Language Models Follow System Messages?](https://mlsanity.com/paper/2408.10943/) (2024)
- [Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models](https://mlsanity.com/paper/2505.14810/) (2025)
- [From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models](https://mlsanity.com/paper/2404.15846/) (2024)
- [RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios](https://mlsanity.com/paper/2412.08972/) (2024)
- [CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints](https://mlsanity.com/paper/2410.04197/) (2024)
- [RubricEval: A Rubric-Level Meta-Evaluation Benchmark for LLM Judges in Instruction Following](https://mlsanity.com/paper/2603.25133/) (2026)
- [The SIFo Benchmark: Investigating the Sequential Instruction Following Ability of Large Language Models](https://mlsanity.com/paper/2406.19999/) (2024)
- [TarGEN: Targeted Data Generation with Large Language Models](https://mlsanity.com/paper/2310.17876/) (2023)
- [Data Management For Training Large Language Models: A Survey](https://mlsanity.com/paper/2312.01700/) (2023)
- [Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models](https://mlsanity.com/paper/2310.07301/) (2023)
- [CLEAR: Can Language Models Really Understand Causal Graphs?](https://mlsanity.com/paper/2406.16605/) (2024)
- [GuideBench: Benchmarking Domain-Oriented Guideline Following for LLM Agents](https://mlsanity.com/paper/2505.11368/) (2025)
- [LLMs can be easily Confused by Instructional Distractions](https://mlsanity.com/paper/2502.04362/) (2025)
- [FollowEval: A Multi-Dimensional Benchmark for Assessing the Instruction-Following Capability of Large Language Models](https://mlsanity.com/paper/2311.09829/) (2023)
- [MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training](https://mlsanity.com/paper/2502.11541/) (2025)
- [Order Matters: Investigate the Position Bias in Multi-constraint Instruction Following](https://mlsanity.com/paper/2502.17204/) (2025)

## Abstract (arXiv)

Large language models (LLMs) can understand human instructions, showing their potential for pragmatic applications beyond traditional NLP tasks. However, they still struggle with complex instructions, which can be either complex task descriptions that require multiple tasks and constraints, or complex input that contains long context, noise, heterogeneous information and multi-turn format. Due to these features, LLMs often ignore semantic constraints from task descriptions, generate incorrect formats, violate length or sample count constraints, and be unfaithful to the input text. Existing benchmarks are insufficient to assess LLMs' ability to understand complex instructions, as they are close-ended and simple. To bridge this gap, we propose CELLO, a benchmark for evaluating LLMs' ability to follow complex instructions systematically. We design eight features for complex instructions and construct a comprehensive evaluation dataset from real-world scenarios. We also establish four criteria and develop corresponding metrics, as current ones are inadequate, biased or too strict and coarse-grained. We compare the performance of representative Chinese-oriented and English-oriented models in following complex instructions through extensive experiments. Resources of CELLO are publicly available at https://github.com/Abbey4799/CELLO.