# Towards Pragmatic Production Strategies for Natural Language Generation Tasks

arXiv: https://arxiv.org/abs/2210.12828 · HTML: https://mlsanity.com/paper/2210.12828/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 32 references that are in the map.
- First posted on arXiv 23 Oct 2022.

## Builds on (most cited first, 6 of 6)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [The PhotoBook Dataset: Building Common Ground through Visually-Grounded Dialogue](https://mlsanity.com/paper/1906.01530/) (2019)
- [Characterizing the dynamics of learning in repeated reference games](https://mlsanity.com/paper/1912.07199/) (2019)
- [A Rate-Distortion view of human pragmatic reasoning](https://mlsanity.com/paper/2005.06641/) (2020)
- [Extending rational models of communication from beliefs to actions](https://mlsanity.com/paper/2105.11950/) (2021)

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

- [Generalized Measures of Anticipation and Responsivity in Online Language Processing](https://mlsanity.com/paper/2409.10728/) (2024)
- [Information Value: Measuring Utterance Predictability as Distance from Plausible Alternatives](https://mlsanity.com/paper/2310.13676/) (2023)
- [Dealing with Semantic Underspecification in Multimodal NLP](https://mlsanity.com/paper/2306.05240/) (2023)
- [Towards Developmentally Plausible Rewards: Communicative Success as a Learning Signal for Interactive Language Models](https://mlsanity.com/paper/2505.05970/) (2025)
- [Measuring Intent Comprehension in LLMs](https://mlsanity.com/paper/2506.16584/) (2025)
- [Surprisal Minimisation over Goal-directed Alternatives Predicts Production Choice in Dialogue](https://mlsanity.com/paper/2605.00506/) (2026)
- [Describe me an Aucklet: Generating Grounded Perceptual Category Descriptions](https://mlsanity.com/paper/2303.04053/) (2023)

## Abstract (arXiv)

This position paper proposes a conceptual framework for the design of Natural Language Generation (NLG) systems that follow efficient and effective production strategies in order to achieve complex communicative goals. In this general framework, efficiency is characterised as the parsimonious regulation of production and comprehension costs while effectiveness is measured with respect to task-oriented and contextually grounded communicative goals. We provide concrete suggestions for the estimation of goals, costs, and utility via modern statistical methods, demonstrating applications of our framework to the classic pragmatic task of visually grounded referential games and to abstractive text summarisation, two popular generation tasks with real-world applications. In sum, we advocate for the development of NLG systems that learn to make pragmatic production decisions from experience, by reasoning about goals, costs, and utility in a human-like way.