# Decoding Methods for Neural Narrative Generation

arXiv: https://arxiv.org/abs/2010.07375 · HTML: https://mlsanity.com/paper/2010.07375/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Oct 2020.

## Built on by (most cited first, 18 of 18)

- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [Locally Typical Sampling](https://mlsanity.com/paper/2202.00666/) (2022)
- [On Decoding Strategies for Neural Text Generators](https://mlsanity.com/paper/2203.15721/) (2022)
- [Do Language Models Plagiarize?](https://mlsanity.com/paper/2203.07618/) (2022)
- [Probing the Creativity of Large Language Models: Can models produce divergent semantic association?](https://mlsanity.com/paper/2310.11158/) (2023)
- [Closing the Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/2310.01693/) (2023)
- [I Cast Detect Thoughts: Learning to Converse and Guide with Intents and Theory-of-Mind in Dungeons and Dragons](https://mlsanity.com/paper/2212.10060/) (2022)
- [FIREBALL: A Dataset of Dungeons and Dragons Actual-Play with Structured Game State Information](https://mlsanity.com/paper/2305.01528/) (2023)
- [Flesch or Fumble? Evaluating Readability Standard Alignment of Instruction-Tuned Language Models](https://mlsanity.com/paper/2309.05454/) (2023)
- [On the probability-quality paradox in language generation](https://mlsanity.com/paper/2203.17217/) (2022)
- [Inspiration through Observation: Demonstrating the Influence of Automatically Generated Text on Creative Writing](https://mlsanity.com/paper/2107.04007/) (2021)
- [Standardize: Aligning Language Models with Expert-Defined Standards for Content Generation](https://mlsanity.com/paper/2402.12593/) (2024)
- [Tachikuma: Understading Complex Interactions with Multi-Character and Novel Objects by Large Language Models](https://mlsanity.com/paper/2307.12573/) (2023)
- [Uniform Complexity for Text Generation](https://mlsanity.com/paper/2204.05185/) (2022)
- [A Continuum of Generation Tasks for Investigating Length Bias and Degenerate Repetition](https://mlsanity.com/paper/2210.10817/) (2022)
- [Anti-LM Decoding for Zero-shot In-context Machine Translation](https://mlsanity.com/paper/2311.08324/) (2023)
- [Multi-Hypothesis Distillation of Multilingual Neural Translation Models for Low-Resource Languages](https://mlsanity.com/paper/2507.21568/) (2025)
- [A Generalized Formalism of Auto-Regressive Decoding for Speech Processing](https://mlsanity.com/paper/2606.20714/) (2026)

## Abstract (arXiv)

Narrative generation is an open-ended NLP task in which a model generates a story given a prompt. The task is similar to neural response generation for chatbots; however, innovations in response generation are often not applied to narrative generation, despite the similarity between these tasks. We aim to bridge this gap by applying and evaluating advances in decoding methods for neural response generation to neural narrative generation. In particular, we employ GPT-2 and perform ablations across nucleus sampling thresholds and diverse decoding hyperparameters -- specifically, maximum mutual information -- analyzing results over multiple criteria with automatic and human evaluation. We find that (1) nucleus sampling is generally best with thresholds between 0.7 and 0.9; (2) a maximum mutual information objective can improve the quality of generated stories; and (3) established automatic metrics do not correlate well with human judgments of narrative quality on any qualitative metric.