# LatticeBridge: Rare-Event Sequential Inference for Faithful Structured Sequence Synthesis

arXiv: https://arxiv.org/abs/2606.11203 · HTML: https://mlsanity.com/paper/2606.11203/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 22 Apr 2026.

## Builds on (most cited first, 20 of 20)

- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [Datasets: A Community Library for Natural Language Processing](https://mlsanity.com/paper/2109.02846/) (2021)
- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [The E2E Dataset: New Challenges For End-to-End Generation](https://mlsanity.com/paper/1706.09254/) (2017)
- [The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics](https://mlsanity.com/paper/2102.01672/) (2021)
- [Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search](https://mlsanity.com/paper/1704.07138/) (2017)
- [Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation](https://mlsanity.com/paper/1804.06609/) (2018)
- [NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics](https://mlsanity.com/paper/2112.08726/) (2021)
- [Elements of Sequential Monte Carlo](https://mlsanity.com/paper/1903.04797/) (2019)
- [Semantic Noise Matters for Neural Natural Language Generation](https://mlsanity.com/paper/1911.03905/) (2019)
- [Automata-based constraints for language model decoding](https://mlsanity.com/paper/2407.08103/) (2024)
- [Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte Carlo](https://mlsanity.com/paper/2410.01920/) (2024)
- [Neural Text Generation from Structured Data with Application to the Biography Domain](https://mlsanity.com/paper/1603.07771/) (2016)
- [Constrained Sampling for Language Models Should Be Easy: An MCMC Perspective](https://mlsanity.com/paper/2506.05754/) (2025)
- [The Hidden Cost of Structured Generation in LLMs: Draft-Conditioned Constrained Decoding](https://mlsanity.com/paper/2603.03305/) (2026)
- [Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators](https://mlsanity.com/paper/2602.22647/) (2026)
- [Thinking Before Constraining: A Unified Decoding Framework for Large Language Models](https://mlsanity.com/paper/2601.07525/) (2026)
- [A*-Decoding: Token-Efficient Inference Scaling](https://mlsanity.com/paper/2505.13672/) (2025)
- [Ensembling Language Models with Sequential Monte Carlo](https://mlsanity.com/paper/2603.05432/) (2026)
- [Improving Constrained Language Generation via Self-Distilled Twisted Sequential Monte Carlo](https://mlsanity.com/paper/2507.02315/) (2025)

## Built on by (most cited first, 1 of 1)

- [Adaptive Multilevel Twisted Sequential Monte Carlo for Rare Events Estimation in Language Models](https://mlsanity.com/paper/2608.21736/) (2026)

## Abstract (arXiv)

Structured sequence generation often requires a model to satisfy several input-derived constraints in a single output. Standard decoding methods may assign high probability to fluent continuations while placing low mass on continuations that realize all required anchors jointly. We study this regime as a rare-event sequential inference problem. LatticeBridge combines a compact prefix language model, instance-compiled surface automata, and a twisted sequential Monte Carlo (SMC) decoder with resampling, multilevel splitting, and a source-support proposal term derived from instance-provided phrases. The constraint representation is compiled from each input instance and does not rely on manually curated lexical classes. On 2,610 attainable validation tasks spanning CommonGen, E2E NLG, and WikiBio, the particle decoder improves exact anchor satisfaction and mean anchor coverage over greedy, beam-filtered, and best-of-k ancestral baselines under a shared proposal model. Since exact anchor satisfaction alone does not rule out unsupported attribute substitutions, the evaluation reports required-anchor coverage, source coverage, source-intrusion diagnostics, overlap, runtime, and particle statistics jointly. The benchmark characterizes the faithfulness-overlap-latency frontier under a fixed proposal model.