# Directed Beam Search: Plug-and-Play Lexically Constrained Language Generation

arXiv: https://arxiv.org/abs/2012.15416 · HTML: https://mlsanity.com/paper/2012.15416/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Dec 2020.

## Built on by (most cited first, 12 of 12)

- [COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics](https://mlsanity.com/paper/2202.11705/) (2022)
- [Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs](https://mlsanity.com/paper/2306.03081/) (2023)
- [Plug-and-Blend: A Framework for Controllable Story Generation with Blended Control Codes](https://mlsanity.com/paper/2104.04039/) (2021)
- [Long-term Control for Dialogue Generation: Methods and Evaluation](https://mlsanity.com/paper/2205.07352/) (2022)
- [Supervised Optimism Correction: Be Confident When LLMs Are Sure](https://mlsanity.com/paper/2504.07527/) (2025)
- [PCAE: A Framework of Plug-in Conditional Auto-Encoder for Controllable Text Generation](https://mlsanity.com/paper/2210.03496/) (2022)
- [Controllable Citation Sentence Generation with Language Models](https://mlsanity.com/paper/2211.07066/) (2022)
- [PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning](https://mlsanity.com/paper/2305.19472/) (2023)
- [Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs](https://mlsanity.com/paper/2506.05387/) (2025)
- [KpopMT: Translation Dataset with Terminology for Kpop Fandom](https://mlsanity.com/paper/2407.07413/) (2024)
- [Incorporating Structure and Chord Constraints in Symbolic Transformer-based Melodic Harmonization](https://mlsanity.com/paper/2512.07627/) (2025)
- [Efficient and Training-Free Control of Language Generation](https://mlsanity.com/paper/2205.06036/) (2022)

## Abstract (arXiv)

Large pre-trained language models are capable of generating realistic text. However, controlling these models so that the generated text satisfies lexical constraints, i.e., contains specific words, is a challenging problem. Given that state-of-the-art language models are too large to be trained from scratch in a manageable time, it is desirable to control these models without re-training them. Methods capable of doing this are called plug-and-play. Recent plug-and-play methods have been successful in constraining small bidirectional language models as well as forward models in tasks with a restricted search space, e.g., machine translation. However, controlling large transformer-based models to meet lexical constraints without re-training them remains a challenge. In this work, we propose Directed Beam Search (DBS), a plug-and-play method for lexically constrained language generation. Our method can be applied to any language model, is easy to implement and can be used for general language generation. In our experiments we use DBS to control GPT-2. We demonstrate its performance on keyword-to-phrase generation and we obtain comparable results as a state-of-the-art non-plug-and-play model for lexically constrained story generation.