# Controllable Text Generation in the Instruction-Tuning Era

arXiv: https://arxiv.org/abs/2405.01490 · HTML: https://mlsanity.com/paper/2405.01490/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 60 references that are in the map.
- First posted on arXiv 2 May 2024.

## Builds on (most cited first, 30 of 44)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [Instruction Tuning for Large Language Models: A Survey](https://mlsanity.com/paper/2308.10792/) (2023)
- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [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)
- [Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM](https://mlsanity.com/paper/2309.14348/) (2023)
- [COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics](https://mlsanity.com/paper/2202.11705/) (2022)
- [NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics](https://mlsanity.com/paper/2112.08726/) (2021)
- [A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models](https://mlsanity.com/paper/2201.05337/) (2022)
- [Energy-based Generative Adversarial Network](https://mlsanity.com/paper/1609.03126/) (2016)
- [Controlled Text Generation with Natural Language Instructions](https://mlsanity.com/paper/2304.14293/) (2023)
- [NaturalProofs: Mathematical Theorem Proving in Natural Language](https://mlsanity.com/paper/2104.01112/) (2021)
- [Controllable Natural Language Generation with Contrastive Prefixes](https://mlsanity.com/paper/2202.13257/) (2022)
- [Evaluating Large Language Models on Controlled Generation Tasks](https://mlsanity.com/paper/2310.14542/) (2023)
- [COLLIE: Systematic Construction of Constrained Text Generation Tasks](https://mlsanity.com/paper/2307.08689/) (2023)
- [Mix and Match: Learning-free Controllable Text Generation using Energy Language Models](https://mlsanity.com/paper/2203.13299/) (2022)

## Built on by (most cited first, 7 of 7)

- [LiSeCo: Linear Semantic Control for Language Generation](https://mlsanity.com/paper/2405.15454/) (2024)
- [Control Large Language Models via Divide and Conquer](https://mlsanity.com/paper/2410.04628/) (2024)
- [Semantic Probabilistic Control of Language Models](https://mlsanity.com/paper/2505.01954/) (2025)
- [LLM-driven Constrained Copy Generation through Iterative Refinement](https://mlsanity.com/paper/2504.10391/) (2025)
- [Fine-grained Controllable Text Generation through In-context Learning with Feedback](https://mlsanity.com/paper/2406.11338/) (2024)
- [Do Retrieval-Augmented Language Models Adapt to Varying User Needs?](https://mlsanity.com/paper/2502.19779/) (2025)
- [AgentCTG: Harnessing Multi-Agent Collaboration for Fine-Grained Precise Control in Text Generation](https://mlsanity.com/paper/2509.13677/) (2025)

## Abstract (arXiv)

While most research on controllable text generation has focused on steering base Language Models, the emerging instruction-tuning and prompting paradigm offers an alternate approach to controllability. We compile and release ConGenBench, a testbed of 17 different controllable generation tasks, using a subset of it to benchmark the performance of 9 different baselines and methods on Instruction-tuned Language Models. To our surprise, we find that prompting-based approaches outperform controllable text generation methods on most datasets and tasks, highlighting a need for research on controllable text generation with Instruction-tuned Language Models in specific. Prompt-based approaches match human performance on most stylistic tasks while lagging on structural tasks, foregrounding a need to study more varied constraints and more challenging stylistic tasks. To facilitate such research, we provide an algorithm that uses only a task dataset and a Large Language Model with in-context capabilities to automatically generate a constraint dataset. This method eliminates the fields dependence on pre-curated constraint datasets, hence vastly expanding the range of constraints that can be studied in the future.