# BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases

arXiv: https://arxiv.org/abs/2305.12018 · HTML: https://mlsanity.com/paper/2305.12018/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 37 references that are in the map.
- First posted on arXiv 19 May 2023.

## Builds on (most cited first, 25 of 25)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [Self-critical Sequence Training for Image Captioning](https://mlsanity.com/paper/1612.00563/) (2016)
- [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)
- [Data Augmentation using Pre-trained Transformer Models](https://mlsanity.com/paper/2003.02245/) (2020)
- [COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics](https://mlsanity.com/paper/2202.11705/) (2022)
- [A Distributional Approach to Controlled Text Generation](https://mlsanity.com/paper/2012.11635/) (2020)
- [Improved Image Captioning via Policy Gradient optimization of SPIDEr](https://mlsanity.com/paper/1612.00370/) (2016)
- [Jigsaw: Large Language Models meet Program Synthesis](https://mlsanity.com/paper/2112.02969/) (2021)
- [Controlled Text Generation as Continuous Optimization with Multiple Constraints](https://mlsanity.com/paper/2108.01850/) (2021)
- [Mix and Match: Learning-free Controllable Text Generation using Energy Language Models](https://mlsanity.com/paper/2203.13299/) (2022)
- [Gradient-Based Constrained Sampling from Language Models](https://mlsanity.com/paper/2205.12558/) (2022)
- [Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation](https://mlsanity.com/paper/2012.02952/) (2020)
- [Exposing the Implicit Energy Networks behind Masked Language Models via Metropolis--Hastings](https://mlsanity.com/paper/2106.02736/) (2021)
- [DisCup: Discriminator Cooperative Unlikelihood Prompt-tuning for Controllable Text Generation](https://mlsanity.com/paper/2210.09551/) (2022)
- [Tailor: A Prompt-Based Approach to Attribute-Based Controlled Text Generation](https://mlsanity.com/paper/2204.13362/) (2022)
- [Controlled Text Generation for Data Augmentation in Intelligent Artificial Agents](https://mlsanity.com/paper/1910.03487/) (2019)
- [Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generation](https://mlsanity.com/paper/2106.15078/) (2021)
- [Differentiable lower bound for expected BLEU score](https://mlsanity.com/paper/1712.04708/) (2017)

## Built on by (most cited first, 24 of 24)

- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability](https://mlsanity.com/paper/2402.08679/) (2024)
- [KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection](https://mlsanity.com/paper/2310.09044/) (2023)
- [FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering](https://mlsanity.com/paper/2504.14492/) (2025)
- [GRACE: Discriminator-Guided Chain-of-Thought Reasoning](https://mlsanity.com/paper/2305.14934/) (2023)
- [DeepEdit: Knowledge Editing as Decoding with Constraints](https://mlsanity.com/paper/2401.10471/) (2024)
- [Automatic Metrics in Natural Language Generation: A Survey of Current Evaluation Practices](https://mlsanity.com/paper/2408.09169/) (2024)
- [Controllable Text Generation in the Instruction-Tuning Era](https://mlsanity.com/paper/2405.01490/) (2024)
- [DiVERT: Distractor Generation with Variational Errors Represented as Text for Math Multiple-choice Questions](https://mlsanity.com/paper/2406.19356/) (2024)
- [BiasFilter: An Inference-Time Debiasing Framework for Large Language Models](https://mlsanity.com/paper/2505.23829/) (2025)
- [Automated Knowledge Component Generation for Interpretable Knowledge Tracing in Coding Problems](https://mlsanity.com/paper/2502.18632/) (2025)
- [nabla-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space](https://mlsanity.com/paper/2603.04948/) (2026)
- [Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs](https://mlsanity.com/paper/2506.05387/) (2025)
- [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)
- [Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing](https://mlsanity.com/paper/2510.12121/) (2025)
- [Linguistically-Controlled Paraphrase Generation](https://mlsanity.com/paper/2410.24199/) (2024)
- [Funny or Persuasive, but Not Both: Evaluating Fine-Grained Multi-Concept Control in LLMs](https://mlsanity.com/paper/2601.18483/) (2026)
- [DRIV-EX: Counterfactual Explanations for Driving LLMs](https://mlsanity.com/paper/2603.00696/) (2026)
- [LingGen: Scalable Multi-Attribute Linguistic Control via Power-Law Masking](https://mlsanity.com/paper/2410.24201/) (2024)
- [Revisiting Transformer Layer Parameterization Through Causal Energy Minimization](https://mlsanity.com/paper/2605.07588/) (2026)
- [Gradient-Guided Reward Optimization for Inference-time Alignment](https://mlsanity.com/paper/2606.09635/) (2026)
- [When Debiasing Backfires: Counterintuitive Side Effects of Preprocessing-Based Stereotype Mitigation](https://mlsanity.com/paper/2607.07937/) (2026)
- [Mitigating Bias in Large Vision-Language Models via Counterfactual Ensemble Decoding](https://mlsanity.com/paper/2608.21415/) (2026)

## Abstract (arXiv)

Energy-based models (EBMs) have gained popularity for controlled text generation due to their high applicability to a wide range of constraints. However, sampling from EBMs is non-trivial, as it often requires a large number of iterations to converge to plausible text, which slows down the decoding process and makes it less practical for real-world applications. In this work, we propose BOLT, which relies on tunable biases to directly adjust the language model's output logits. Unlike prior work, BOLT maintains the generator's autoregressive nature to assert a strong control on token-wise conditional dependencies and overall fluency, and thus converges faster. When compared with state-of-the-arts on controlled generation tasks using both soft constraints (e.g., sentiment control) and hard constraints (e.g., keyword-guided topic control), BOLT demonstrates significantly improved efficiency and fluency. On sentiment control, BOLT is 7x faster than competitive baselines, and more fluent in 74.4% of the evaluation samples according to human judges.