# Maximizing Stylistic Control and Semantic Accuracy in NLG: Personality Variation and Discourse Contrast

arXiv: https://arxiv.org/abs/1907.09527 · HTML: https://mlsanity.com/paper/1907.09527/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jul 2019.

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

- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models](https://mlsanity.com/paper/2402.02896/) (2024)
- [Controlling Personality Style in Dialogue with Zero-Shot Prompt-Based Learning](https://mlsanity.com/paper/2302.03848/) (2023)
- [On the Effectiveness of Creating Conversational Agent Personalities Through Prompting](https://mlsanity.com/paper/2310.11182/) (2023)
- [Jurassic is (almost) All You Need: Few-Shot Meaning-to-Text Generation for Open-Domain Dialogue](https://mlsanity.com/paper/2110.08094/) (2021)
- [A Survey of Personality, Persona, and Profile in Conversational Agents and Chatbots](https://mlsanity.com/paper/2401.00609/) (2023)
- [Athena 2.0: Contextualized Dialogue Management for an Alexa Prize SocialBot](https://mlsanity.com/paper/2111.02519/) (2021)
- [Controllable Generation of Dialogue Acts for Dialogue Systems via Few-Shot Response Generation and Ranking](https://mlsanity.com/paper/2307.14440/) (2023)
- [A Systematic Review of Data-to-Text NLG](https://mlsanity.com/paper/2402.08496/) (2024)
- [The Bots of Persuasion: Examining How Conversational Agents' Linguistic Expressions of Personality Affect User Perceptions and Decisions](https://mlsanity.com/paper/2602.17185/) (2026)
- [Athena 2.0: Discourse and User Modeling in Open Domain Dialogue](https://mlsanity.com/paper/2308.01887/) (2023)
- [Source Prompt: Coordinated Pre-training of Language Models on Diverse Corpora from Multiple Sources](https://mlsanity.com/paper/2311.09732/) (2023)

## Abstract (arXiv)

Neural generation methods for task-oriented dialogue typically generate from a meaning representation that is populated using a database of domain information, such as a table of data describing a restaurant. While earlier work focused solely on the semantic fidelity of outputs, recent work has started to explore methods for controlling the style of the generated text while simultaneously achieving semantic accuracy. Here we experiment with two stylistic benchmark tasks, generating language that exhibits variation in personality, and generating discourse contrast. We report a huge performance improvement in both stylistic control and semantic accuracy over the state of the art on both of these benchmarks. We test several different models and show that putting stylistic conditioning in the decoder and eliminating the semantic re-ranker used in earlier models results in more than 15 points higher BLEU for Personality, with a reduction of semantic error to near zero. We also report an improvement from .75 to .81 in controlling contrast and a reduction in semantic error from 16% to 2%.