# Posterior Control of Blackbox Generation

arXiv: https://arxiv.org/abs/2005.04560 · HTML: https://mlsanity.com/paper/2005.04560/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 May 2020.

## Built on by (most cited first, 16 of 16)

- [A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation](https://mlsanity.com/paper/2104.08704/) (2021)
- [Sequence-to-Sequence Learning with Latent Neural Grammars](https://mlsanity.com/paper/2109.01135/) (2021)
- [Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View](https://mlsanity.com/paper/2102.08585/) (2021)
- [Data-to-text Generation with Variational Sequential Planning](https://mlsanity.com/paper/2202.13756/) (2022)
- [Towards Verifiable Text Generation with Symbolic References](https://mlsanity.com/paper/2311.09188/) (2023)
- [Inducing and Using Alignments for Transition-based AMR Parsing](https://mlsanity.com/paper/2205.01464/) (2022)
- [GenNI: Human-AI Collaboration for Data-Backed Text Generation](https://mlsanity.com/paper/2110.10185/) (2021)
- [AGGGEN: Ordering and Aggregating while Generating](https://mlsanity.com/paper/2106.05580/) (2021)
- [Latent Topology Induction for Understanding Contextualized Representations](https://mlsanity.com/paper/2206.01512/) (2022)
- [AutoTemplate: A Simple Recipe for Lexically Constrained Text Generation](https://mlsanity.com/paper/2211.08387/) (2022)
- [Data-to-text Generation by Splicing Together Nearest Neighbors](https://mlsanity.com/paper/2101.08248/) (2021)
- [TempLM: Distilling Language Models into Template-Based Generators](https://mlsanity.com/paper/2205.11055/) (2022)
- [Scaling Structured Inference with Randomization](https://mlsanity.com/paper/2112.03638/) (2021)
- [Automatic Logical Forms improve fidelity in Table-to-Text generation](https://mlsanity.com/paper/2310.17279/) (2023)
- [Empirical Sufficiency Lower Bounds for Language Modeling with Locally-Bootstrapped Semantic Structures](https://mlsanity.com/paper/2305.18915/) (2023)
- [CRAMER: Control via Request-Aware Masking for Editing Recommenders](https://mlsanity.com/paper/2608.25370/) (2026)

## Abstract (arXiv)

Text generation often requires high-precision output that obeys task-specific rules. This fine-grained control is difficult to enforce with off-the-shelf deep learning models. In this work, we consider augmenting neural generation models with discrete control states learned through a structured latent-variable approach. Under this formulation, task-specific knowledge can be encoded through a range of rich, posterior constraints that are effectively trained into the model. This approach allows users to ground internal model decisions based on prior knowledge, without sacrificing the representational power of neural generative models. Experiments consider applications of this approach for text generation. We find that this method improves over standard benchmarks, while also providing fine-grained control.