# Comparison of Diverse Decoding Methods from Conditional Language Models

arXiv: https://arxiv.org/abs/1906.06362 · HTML: https://mlsanity.com/paper/1906.06362/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2019.

## Built on by (most cited first, 30 of 78)

- [NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics](https://mlsanity.com/paper/2112.08726/) (2021)
- [LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks](https://mlsanity.com/paper/2206.06565/) (2022)
- [Towards Making the Most of ChatGPT for Machine Translation](https://mlsanity.com/paper/2303.13780/) (2023)
- [Advances and Challenges in Conversational Recommender Systems: A Survey](https://mlsanity.com/paper/2101.09459/) (2021)
- [A Thorough Examination of Decoding Methods in the Era of LLMs](https://mlsanity.com/paper/2402.06925/) (2024)
- [ARGS: Alignment as Reward-Guided Search](https://mlsanity.com/paper/2402.01694/) (2024)
- [The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text](https://mlsanity.com/paper/2311.09807/) (2023)
- [On Decoding Strategies for Neural Text Generators](https://mlsanity.com/paper/2203.15721/) (2022)
- [Sparks: Inspiration for Science Writing using Language Models](https://mlsanity.com/paper/2110.07640/) (2021)
- [Jointly Reinforcing Diversity and Quality in Language Model Generations](https://mlsanity.com/paper/2509.02534/) (2025)
- [ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering](https://mlsanity.com/paper/2401.07333/) (2024)
- [Modifying Large Language Model Post-Training for Diverse Creative Writing](https://mlsanity.com/paper/2503.17126/) (2025)
- [Improving Uncertainty Estimation through Semantically Diverse Language Generation](https://mlsanity.com/paper/2406.04306/) (2024)
- [Closing the Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/2310.01693/) (2023)
- [Diversifying Dialog Generation via Adaptive Label Smoothing](https://mlsanity.com/paper/2105.14556/) (2021)
- [Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs](https://mlsanity.com/paper/2402.05864/) (2024)
- [Why is constrained neural language generation particularly challenging?](https://mlsanity.com/paper/2206.05395/) (2022)
- [ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning](https://mlsanity.com/paper/2105.12995/) (2021)
- [Controllable Text Summarization: Unraveling Challenges, Approaches, and Prospects -- A Survey](https://mlsanity.com/paper/2311.09212/) (2023)
- [Evaluating Diversity in Automatic Poetry Generation](https://mlsanity.com/paper/2406.15267/) (2024)
- [GeAR: Graph-enhanced Agent for Retrieval-augmented Generation](https://mlsanity.com/paper/2412.18431/) (2024)
- [On the probability-quality paradox in language generation](https://mlsanity.com/paper/2203.17217/) (2022)
- [Not Just Novelty: A Longitudinal Study on Utility and Customization of an AI Workflow](https://mlsanity.com/paper/2402.09894/) (2024)
- [A New Approach to Overgenerating and Scoring Abstractive Summaries](https://mlsanity.com/paper/2104.01726/) (2021)
- [PathFinder: Guided Search over Multi-Step Reasoning Paths](https://mlsanity.com/paper/2312.05180/) (2023)
- [Tweetorial Hooks: Generative AI Tools to Motivate Science on Social Media](https://mlsanity.com/paper/2305.12265/) (2023)
- [Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding](https://mlsanity.com/paper/2401.05054/) (2024)
- [Diverse and Specific Clarification Question Generation with Keywords](https://mlsanity.com/paper/2104.10317/) (2021)
- [Efficient Beam Search for Large Language Models Using Trie-Based Decoding](https://mlsanity.com/paper/2502.00085/) (2025)
- [Generating EDU Extracts for Plan-Guided Summary Re-Ranking](https://mlsanity.com/paper/2305.17779/) (2023)

## Abstract (arXiv)

While conditional language models have greatly improved in their ability to output high-quality natural language, many NLP applications benefit from being able to generate a diverse set of candidate sequences. Diverse decoding strategies aim to, within a given-sized candidate list, cover as much of the space of high-quality outputs as possible, leading to improvements for tasks that re-rank and combine candidate outputs. Standard decoding methods, such as beam search, optimize for generating high likelihood sequences rather than diverse ones, though recent work has focused on increasing diversity in these methods. In this work, we perform an extensive survey of decoding-time strategies for generating diverse outputs from conditional language models. We also show how diversity can be improved without sacrificing quality by over-sampling additional candidates, then filtering to the desired number.