# Steering Output Style and Topic in Neural Response Generation

arXiv: https://arxiv.org/abs/1709.03010 · HTML: https://mlsanity.com/paper/1709.03010/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Sep 2017.

## Built on by (most cited first, 10 of 10)

- [Generating Summaries with Controllable Readability Levels](https://mlsanity.com/paper/2310.10623/) (2023)
- [Why is constrained neural language generation particularly challenging?](https://mlsanity.com/paper/2206.05395/) (2022)
- [Generating Relevant and Coherent Dialogue Responses using Self-separated Conditional Variational AutoEncoders](https://mlsanity.com/paper/2106.03410/) (2021)
- [HydraSum: Disentangling Stylistic Features in Text Summarization using Multi-Decoder Models](https://mlsanity.com/paper/2110.04400/) (2021)
- [Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue](https://mlsanity.com/paper/2402.06967/) (2024)
- [Towards Standard Criteria for human evaluation of Chatbots: A Survey](https://mlsanity.com/paper/2105.11197/) (2021)
- [Controllable Dialogue Generation with Disentangled Multi-grained Style Specification and Attribute Consistency Reward](https://mlsanity.com/paper/2109.06717/) (2021)
- [ConsistentChat: Building Skeleton-Guided Consistent Multi-Turn Dialogues for Large Language Models from Scratch](https://mlsanity.com/paper/2506.03558/) (2025)
- [DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines](https://mlsanity.com/paper/2212.10557/) (2022)
- [Psychology-guided Controllable Story Generation](https://mlsanity.com/paper/2210.07493/) (2022)

## Abstract (arXiv)

We propose simple and flexible training and decoding methods for influencing output style and topic in neural encoder-decoder based language generation. This capability is desirable in a variety of applications, including conversational systems, where successful agents need to produce language in a specific style and generate responses steered by a human puppeteer or external knowledge. We decompose the neural generation process into empirically easier sub-problems: a faithfulness model and a decoding method based on selective-sampling. We also describe training and sampling algorithms that bias the generation process with a specific language style restriction, or a topic restriction. Human evaluation results show that our proposed methods are able to restrict style and topic without degrading output quality in conversational tasks.