# Benchmarking Large Language Models on Controllable Generation under Diversified Instructions

arXiv: https://arxiv.org/abs/2401.00690 · HTML: https://mlsanity.com/paper/2401.00690/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 41 references that are in the map.
- First posted on arXiv 1 Jan 2024.

## Builds on (most cited first, 28 of 28)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [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)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [RWKV: Reinventing RNNs for the Transformer Era](https://mlsanity.com/paper/2305.13048/) (2023)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models](https://mlsanity.com/paper/2305.08322/) (2023)
- [Is ChatGPT a General-Purpose Natural Language Processing Task Solver?](https://mlsanity.com/paper/2302.06476/) (2023)
- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor](https://mlsanity.com/paper/2212.09689/) (2022)
- [GeDi: Generative Discriminator Guided Sequence Generation](https://mlsanity.com/paper/2009.06367/) (2020)
- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)
- [The Vendi Score: A Diversity Evaluation Metric for Machine Learning](https://mlsanity.com/paper/2210.02410/) (2022)
- [Quark: Controllable Text Generation with Reinforced Unlearning](https://mlsanity.com/paper/2205.13636/) (2022)
- [COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics](https://mlsanity.com/paper/2202.11705/) (2022)
- [Controlled Text Generation with Natural Language Instructions](https://mlsanity.com/paper/2304.14293/) (2023)
- [Controllable Natural Language Generation with Contrastive Prefixes](https://mlsanity.com/paper/2202.13257/) (2022)
- [RewriteLM: An Instruction-Tuned Large Language Model for Text Rewriting](https://mlsanity.com/paper/2305.15685/) (2023)
- [Positional Encoding to Control Output Sequence Length](https://mlsanity.com/paper/1904.07418/) (2019)
- [A Distributional Lens for Multi-Aspect Controllable Text Generation](https://mlsanity.com/paper/2210.02889/) (2022)
- [Bounding the Capabilities of Large Language Models in Open Text Generation with Prompt Constraints](https://mlsanity.com/paper/2302.09185/) (2023)
- [DisCup: Discriminator Cooperative Unlikelihood Prompt-tuning for Controllable Text Generation](https://mlsanity.com/paper/2210.09551/) (2022)
- [CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generation](https://mlsanity.com/paper/2204.00862/) (2022)

## Built on by (most cited first, 27 of 27)

- [Benchmarking Complex Instruction-Following with Multiple Constraints Composition](https://mlsanity.com/paper/2407.03978/) (2024)
- [FOFO: A Benchmark to Evaluate LLMs' Format-Following Capability](https://mlsanity.com/paper/2402.18667/) (2024)
- [Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents](https://mlsanity.com/paper/2402.00798/) (2024)
- [Learning to Generate Structured Output with Schema Reinforcement Learning](https://mlsanity.com/paper/2502.18878/) (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)
- [LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs](https://mlsanity.com/paper/2408.08656/) (2024)
- [The SIFo Benchmark: Investigating the Sequential Instruction Following Ability of Large Language Models](https://mlsanity.com/paper/2406.19999/) (2024)
- [MobileAIBench: Benchmarking LLMs and LMMs for On-Device Use Cases](https://mlsanity.com/paper/2406.10290/) (2024)
- [PersoBench: Benchmarking Personalized Response Generation in Large Language Models](https://mlsanity.com/paper/2410.03198/) (2024)
- [MARS: Benchmarking the Metaphysical Reasoning Abilities of Language Models with a Multi-task Evaluation Dataset](https://mlsanity.com/paper/2406.02106/) (2024)
- [RuleR: Improving LLM Controllability by Rule-based Data Recycling](https://mlsanity.com/paper/2406.15938/) (2024)
- [XIFBench: Evaluating Large Language Models on Multilingual Instruction Following](https://mlsanity.com/paper/2503.07539/) (2025)
- [Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks](https://mlsanity.com/paper/2410.22296/) (2024)
- [Zero-Shot Strategies for Length-Controllable Summarization](https://mlsanity.com/paper/2501.00233/) (2024)
- [Does higher interpretability imply better utility? A Pairwise Analysis on Sparse Autoencoders](https://mlsanity.com/paper/2510.03659/) (2025)
- [ConInstruct: Evaluating Large Language Models on Conflict Detection and Resolution in Instructions](https://mlsanity.com/paper/2511.14342/) (2025)
- [Divide-Verify-Refine: Can LLMs Self-Align with Complex Instructions?](https://mlsanity.com/paper/2410.12207/) (2024)
- [Revisiting the Reliability of Language Models in Instruction-Following](https://mlsanity.com/paper/2512.14754/) (2025)
- [A Survey of RWKV](https://mlsanity.com/paper/2412.14847/) (2024)
- [Preference-Guided Reflective Sampling for Aligning Language Models](https://mlsanity.com/paper/2408.12163/) (2024)
- [Too Easily Fooled? Prompt Injection Breaks LLMs on Frustratingly Simple Multiple-Choice Questions](https://mlsanity.com/paper/2508.13214/) (2025)
- [On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions](https://mlsanity.com/paper/2406.10885/) (2024)
- [EvalYaks: Instruction Tuning Datasets and LoRA Fine-tuned Models for Automated Scoring of CEFR B2 Speaking Assessment Transcripts](https://mlsanity.com/paper/2408.12226/) (2024)
- [How Instruction-Tuning Imparts Length Control: A Cross-Lingual Mechanistic Analysis](https://mlsanity.com/paper/2509.02075/) (2025)
- [Towards Lightweight, Adaptive and Attribute-Aware Multi-Aspect Controllable Text Generation with Large Language Models](https://mlsanity.com/paper/2502.13474/) (2025)
- [When Verifiable Counts Depend on Wording: Auditing Wording Robustness in Instruction Following](https://mlsanity.com/paper/2610.05278/) (2026)

## Abstract (arXiv)

While large language models (LLMs) have exhibited impressive instruction-following capabilities, it is still unclear whether and to what extent they can respond to explicit constraints that might be entailed in various instructions. As a significant aspect of LLM alignment, it is thus important to formulate such a specialized set of instructions as well as investigate the resulting behavior of LLMs. To address this vacancy, we propose a new benchmark CoDI-Eval to systematically and comprehensively evaluate LLMs' responses to instructions with various constraints. We construct a large collection of constraints-attributed instructions as a test suite focused on both generalization and coverage. Specifically, we advocate an instruction diversification process to synthesize diverse forms of constraint expression and also deliberate the candidate task taxonomy with even finer-grained sub-categories. Finally, we automate the entire evaluation process to facilitate further developments. Different from existing studies on controllable text generation, CoDI-Eval extends the scope to the prevalent instruction-following paradigm for the first time. We provide extensive evaluations of representative LLMs (e.g., ChatGPT, Vicuna) on CoDI-Eval, revealing their limitations in following instructions with specific constraints and there is still a significant gap between open-source and commercial closed-source LLMs. We believe this benchmark will facilitate research into improving the controllability of LLMs' responses to instructions. Our data and code are available at https://github.com/Xt-cyh/CoDI-Eval.