# Neural Particle Smoothing for Sampling from Conditional Sequence Models

arXiv: https://arxiv.org/abs/1804.10747 · HTML: https://mlsanity.com/paper/1804.10747/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Apr 2018.

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

- [Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo](https://mlsanity.com/paper/2504.13139/) (2025)
- [Anticipatory Music Transformer](https://mlsanity.com/paper/2306.08620/) (2023)
- [Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Sampling](https://mlsanity.com/paper/2504.05410/) (2025)
- [ACCoRD: A Multi-Document Approach to Generating Diverse Descriptions of Scientific Concepts](https://mlsanity.com/paper/2205.06982/) (2022)
- [Autoregressive Modeling with Lookahead Attention](https://mlsanity.com/paper/2305.12272/) (2023)
- [Type-Compliant Adaptation Cascades: Adapting Programmatic LM Workflows to Data](https://mlsanity.com/paper/2508.18244/) (2025)
- [Structure-Aware Path Inference for Neural Finite State Transducers](https://mlsanity.com/paper/2312.13614/) (2023)

## Abstract (arXiv)

We introduce neural particle smoothing, a sequential Monte Carlo method for sampling annotations of an input string from a given probability model. In contrast to conventional particle filtering algorithms, we train a proposal distribution that looks ahead to the end of the input string by means of a right-to-left LSTM. We demonstrate that this innovation can improve the quality of the sample. To motivate our formal choices, we explain how our neural model and neural sampler can be viewed as low-dimensional but nonlinear approximations to working with HMMs over very large state spaces.