# CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models

arXiv: https://arxiv.org/abs/2402.13109 · HTML: https://mlsanity.com/paper/2402.13109/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 67 references that are in the map.
- First posted on arXiv 20 Feb 2024.

## Builds on (most cited first, 30 of 43)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [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)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs](https://mlsanity.com/paper/1903.00161/) (2019)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models](https://mlsanity.com/paper/2305.08322/) (2023)
- [Cross-Task Generalization via Natural Language Crowdsourcing Instructions](https://mlsanity.com/paper/2104.08773/) (2021)
- [CoQA: A Conversational Question Answering Challenge](https://mlsanity.com/paper/1808.07042/) (2018)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [Baichuan 2: Open Large-scale Language Models](https://mlsanity.com/paper/2309.10305/) (2023)
- [UnifiedQA: Crossing Format Boundaries With a Single QA System](https://mlsanity.com/paper/2005.00700/) (2020)
- [CMMLU: Measuring massive multitask language understanding in Chinese](https://mlsanity.com/paper/2306.09212/) (2023)
- [NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark](https://mlsanity.com/paper/2310.18018/) (2023)
- [TextWorld: A Learning Environment for Text-based Games](https://mlsanity.com/paper/1806.11532/) (2018)
- [Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca](https://mlsanity.com/paper/2304.08177/) (2023)
- [PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts](https://mlsanity.com/paper/2202.01279/) (2022)
- [CLUE: A Chinese Language Understanding Evaluation Benchmark](https://mlsanity.com/paper/2004.05986/) (2020)
- [The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics](https://mlsanity.com/paper/2102.01672/) (2021)
- [TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs](https://mlsanity.com/paper/2303.16434/) (2023)
- [CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP](https://mlsanity.com/paper/2104.08835/) (2021)
- [Multilingual Large Language Models Are Not (Yet) Code-Switchers](https://mlsanity.com/paper/2305.14235/) (2023)
- [MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative Tasks](https://mlsanity.com/paper/2109.06275/) (2021)
- [Precedent-Enhanced Legal Judgment Prediction with LLM and Domain-Model Collaboration](https://mlsanity.com/paper/2310.09241/) (2023)

## Built on by (most cited first, 11 of 11)

- [Survey of Cultural Awareness in Language Models: Text and Beyond](https://mlsanity.com/paper/2411.00860/) (2024)
- [Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model](https://mlsanity.com/paper/2404.04167/) (2024)
- [MIRA: Medical Time Series Foundation Model for Real-World Health Data](https://mlsanity.com/paper/2506.07584/) (2025)
- [Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models](https://mlsanity.com/paper/2506.01413/) (2025)
- [MulDimIF: A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models](https://mlsanity.com/paper/2505.07591/) (2025)
- [ReasonIF: Large Reasoning Models Fail to Follow Instructions During Reasoning](https://mlsanity.com/paper/2510.15211/) (2025)
- [XIFBench: Evaluating Large Language Models on Multilingual Instruction Following](https://mlsanity.com/paper/2503.07539/) (2025)
- [Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?](https://mlsanity.com/paper/2509.04292/) (2025)
- [TarDiff: Target-Oriented Diffusion Guidance for Synthetic Electronic Health Record Time Series Generation](https://mlsanity.com/paper/2504.17613/) (2025)
- [DICE: Structured Reasoning in LLMs through SLM-Guided Chain-of-Thought Correction](https://mlsanity.com/paper/2510.09211/) (2025)
- [CAPITU: A Benchmark for Evaluating Instruction-Following in Brazilian Portuguese with Literary Context](https://mlsanity.com/paper/2603.22576/) (2026)

## Abstract (arXiv)

The advancement of large language models (LLMs) has enhanced the ability to generalize across a wide range of unseen natural language processing (NLP) tasks through instruction-following. Yet, their effectiveness often diminishes in low-resource languages like Chinese, exacerbated by biased evaluations from data leakage, casting doubt on their true generalizability to new linguistic territories. In response, we introduce the Chinese Instruction-Following Benchmark (CIF-Bench), designed to evaluate the zero-shot generalizability of LLMs to the Chinese language. CIF-Bench comprises 150 tasks and 15,000 input-output pairs, developed by native speakers to test complex reasoning and Chinese cultural nuances across 20 categories. To mitigate data contamination, we release only half of the dataset publicly, with the remainder kept private, and introduce diversified instructions to minimize score variance, totaling 45,000 data instances. Our evaluation of 28 selected LLMs reveals a noticeable performance gap, with the best model scoring only 52.9%, highlighting the limitations of LLMs in less familiar language and task contexts. This work not only uncovers the current limitations of LLMs in handling Chinese language tasks but also sets a new standard for future LLM generalizability research, pushing towards the development of more adaptable, culturally informed, and linguistically diverse models.