# PREADD: Prefix-Adaptive Decoding for Controlled Text Generation

arXiv: https://arxiv.org/abs/2307.03214 · HTML: https://mlsanity.com/paper/2307.03214/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 51 references that are in the map.
- First posted on arXiv 6 Jul 2023.

## Builds on (most cited first, 27 of 27)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [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)
- [Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP](https://mlsanity.com/paper/2103.00453/) (2021)
- [Measurement and Fairness](https://mlsanity.com/paper/1912.05511/) (2019)
- [Latent Hatred: A Benchmark for Understanding Implicit Hate Speech](https://mlsanity.com/paper/2109.05322/) (2021)
- [Detoxifying Language Models Risks Marginalizing Minority Voices](https://mlsanity.com/paper/2104.06390/) (2021)
- [Hate Speech Detection and Racial Bias Mitigation in Social Media based on BERT model](https://mlsanity.com/paper/2008.06460/) (2020)
- [The Radicalization Risks of GPT-3 and Advanced Neural Language Models](https://mlsanity.com/paper/2009.06807/) (2020)
- [Controllable Generation from Pre-trained Language Models via Inverse Prompting](https://mlsanity.com/paper/2103.10685/) (2021)
- [Why is constrained neural language generation particularly challenging?](https://mlsanity.com/paper/2206.05395/) (2022)

## Built on by (most cited first, 29 of 29)

- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Tuning Language Models by Proxy](https://mlsanity.com/paper/2401.08565/) (2024)
- [Controlled Text Generation via Language Model Arithmetic](https://mlsanity.com/paper/2311.14479/) (2023)
- [Parallel Scaling Law for Language Models](https://mlsanity.com/paper/2505.10475/) (2025)
- [When One LLM Drools, Multi-LLM Collaboration Rules](https://mlsanity.com/paper/2502.04506/) (2025)
- [SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models](https://mlsanity.com/paper/2406.12274/) (2024)
- [Automatic Metrics in Natural Language Generation: A Survey of Current Evaluation Practices](https://mlsanity.com/paper/2408.09169/) (2024)
- [Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs](https://mlsanity.com/paper/2402.11218/) (2024)
- [Selective Prompt Anchoring for Code Generation](https://mlsanity.com/paper/2408.09121/) (2024)
- [G2: Guided Generation for Enhanced Output Diversity in LLMs](https://mlsanity.com/paper/2511.00432/) (2025)
- [RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework](https://mlsanity.com/paper/2410.19109/) (2024)
- [Measuring and Guiding Monosemanticity](https://mlsanity.com/paper/2506.19382/) (2025)
- [Don't Throw Away Your Pretrained Model](https://mlsanity.com/paper/2510.09913/) (2025)
- [DESTEIN: Navigating Detoxification of Language Models via Universal Steering Pairs and Head-wise Activation Fusion](https://mlsanity.com/paper/2404.10464/) (2024)
- [SCAR: Sparse Conditioned Autoencoders for Concept Detection and Steering in LLMs](https://mlsanity.com/paper/2411.07122/) (2024)
- [Speculative Safety-Aware Decoding](https://mlsanity.com/paper/2508.17739/) (2025)
- [JAM: Controllable and Responsible Text Generation via Causal Reasoning and Latent Vector Manipulation](https://mlsanity.com/paper/2502.20684/) (2025)
- [Questionable practices in machine learning](https://mlsanity.com/paper/2407.12220/) (2024)
- [VTechAGP: An Academic-to-General-Audience Text Paraphrase Dataset and Benchmark Models](https://mlsanity.com/paper/2411.04825/) (2024)
- [LaSEr-Edit: Localized Span-level Error Editing with Energy-based Localization](https://mlsanity.com/paper/2407.00740/) (2024)
- [Palette of Language Models: A Solver for Controlled Text Generation](https://mlsanity.com/paper/2503.11182/) (2025)
- [The Single-Multi Evolution Loop for Self-Improving Model Collaboration Systems](https://mlsanity.com/paper/2602.05182/) (2026)
- [CPT: Consistent Proxy Tuning for Black-box Optimization](https://mlsanity.com/paper/2407.01155/) (2024)
- [LaPA2: Length-Aware Prefix and Prompt Attention Augmentation for Long-Form Controllable Text Generation](https://mlsanity.com/paper/2508.04047/) (2025)
- [LingGen: Scalable Multi-Attribute Linguistic Control via Power-Law Masking](https://mlsanity.com/paper/2410.24201/) (2024)
- [Interweaving Memories of a Siamese Large Language Model](https://mlsanity.com/paper/2412.17383/) (2024)
- [CLEAR: Contrasting Textual Feedback with Experts and Amateurs for Reasoning](https://mlsanity.com/paper/2504.07116/) (2025)
- [AgentCTG: Harnessing Multi-Agent Collaboration for Fine-Grained Precise Control in Text Generation](https://mlsanity.com/paper/2509.13677/) (2025)
- [Guidance Is Not a Hyperparameter: Learning Dynamic Control in Diffusion Language Models](https://mlsanity.com/paper/2605.07701/) (2026)

## Abstract (arXiv)

We propose Prefix-Adaptive Decoding (PREADD), a flexible method for controlled text generation. Unlike existing methods that use auxiliary expert models to control for attributes, PREADD does not require an external model, instead relying on linearly combining output logits from multiple prompts. Specifically, PREADD contrasts the output logits generated using a raw prompt against those generated using a prefix-prepended prompt, enabling both positive and negative control with respect to any attribute encapsulated by the prefix. We evaluate PREADD on three tasks -- toxic output mitigation, gender bias reduction, and sentiment control -- and find that PREADD outperforms not only prompting baselines, but also an auxiliary-expert control method, by 12% or more in relative gain on our main metrics for each task.