# Trading Off Diversity and Quality in Natural Language Generation

arXiv: https://arxiv.org/abs/2004.10450 · HTML: https://mlsanity.com/paper/2004.10450/

## Key facts

- Cited by 96 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2020.

## Built on by (most cited first, 30 of 96)

- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers](https://mlsanity.com/paper/2102.01454/) (2021)
- [DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models](https://mlsanity.com/paper/2210.08933/) (2022)
- [SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control](https://mlsanity.com/paper/2210.17432/) (2022)
- [Scalable Best-of-N Selection for Large Language Models via Self-Certainty](https://mlsanity.com/paper/2502.18581/) (2025)
- [From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models](https://mlsanity.com/paper/2406.16838/) (2024)
- [Locally Typical Sampling](https://mlsanity.com/paper/2202.00666/) (2022)
- [The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text](https://mlsanity.com/paper/2311.09807/) (2023)
- [Is Temperature the Creativity Parameter of Large Language Models?](https://mlsanity.com/paper/2405.00492/) (2024)
- [On Decoding Strategies for Neural Text Generators](https://mlsanity.com/paper/2203.15721/) (2022)
- [Effective Prompt Extraction from Language Models](https://mlsanity.com/paper/2307.06865/) (2023)
- [Jointly Reinforcing Diversity and Quality in Language Model Generations](https://mlsanity.com/paper/2509.02534/) (2025)
- [Do Language Models Plagiarize?](https://mlsanity.com/paper/2203.07618/) (2022)
- [RankGen: Improving Text Generation with Large Ranking Models](https://mlsanity.com/paper/2205.09726/) (2022)
- [Real or Fake Text?: Investigating Human Ability to Detect Boundaries Between Human-Written and Machine-Generated Text](https://mlsanity.com/paper/2212.12672/) (2022)
- [Diverse Preference Optimization](https://mlsanity.com/paper/2501.18101/) (2025)
- [Evaluating the Diversity and Quality of LLM Generated Content](https://mlsanity.com/paper/2504.12522/) (2025)
- [Forcing Diffuse Distributions out of Language Models](https://mlsanity.com/paper/2404.10859/) (2024)
- [KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection](https://mlsanity.com/paper/2310.09044/) (2023)
- [Modifying Large Language Model Post-Training for Diverse Creative Writing](https://mlsanity.com/paper/2503.17126/) (2025)
- [Benchmarking Linguistic Diversity of Large Language Models](https://mlsanity.com/paper/2412.10271/) (2024)
- [The Homogenizing Effect of Large Language Models on Human Expression and Thought](https://mlsanity.com/paper/2508.01491/) (2025)
- [Probing the Creativity of Large Language Models: Can models produce divergent semantic association?](https://mlsanity.com/paper/2310.11158/) (2023)
- [A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generation](https://mlsanity.com/paper/2203.15108/) (2022)
- [Mitigating Hallucinations in Large Vision-Language Models (LVLMs) via Language-Contrastive Decoding (LCD)](https://mlsanity.com/paper/2408.04664/) (2024)
- [Collective Critics for Creative Story Generation](https://mlsanity.com/paper/2410.02428/) (2024)
- [On the Efficacy of Sampling Adapters](https://mlsanity.com/paper/2307.03749/) (2023)
- [Vision-Language Instruction Tuning: A Review and Analysis](https://mlsanity.com/paper/2311.08172/) (2023)
- [On the probability-quality paradox in language generation](https://mlsanity.com/paper/2203.17217/) (2022)

## Abstract (arXiv)

For open-ended language generation tasks such as storytelling and dialogue, choosing the right decoding algorithm is critical to controlling the tradeoff between generation quality and diversity. However, there presently exists no consensus on which decoding procedure is best or even the criteria by which to compare them. We address these issues by casting decoding as a multi-objective optimization problem aiming to simultaneously maximize both response quality and diversity. Our framework enables us to perform the first large-scale evaluation of decoding methods along the entire quality-diversity spectrum. We find that when diversity is a priority, all methods perform similarly, but when quality is viewed as more important, the recently proposed nucleus sampling (Holtzman et al. 2019) outperforms all other evaluated decoding algorithms. Our experiments also confirm the existence of the `likelihood trap', the counter-intuitive observation that high likelihood sequences are often surprisingly low quality. We leverage our findings to create and evaluate an algorithm called selective sampling which tractably approximates globally-normalized temperature sampling.