# Growing a Tail: Increasing Output Diversity in Large Language Models

arXiv: https://arxiv.org/abs/2411.02989 · HTML: https://mlsanity.com/paper/2411.02989/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 30 references that are in the map.
- First posted on arXiv 5 Nov 2024.

## Builds on (most cited first, 22 of 22)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias](https://mlsanity.com/paper/2306.15895/) (2023)
- [Tool Learning with Large Language Models: A Survey](https://mlsanity.com/paper/2405.17935/) (2024)
- [COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics](https://mlsanity.com/paper/2202.11705/) (2022)
- [Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs](https://mlsanity.com/paper/2407.01082/) (2024)
- [Language Models as Agent Models](https://mlsanity.com/paper/2212.01681/) (2022)
- [Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventions](https://mlsanity.com/paper/2306.04140/) (2023)
- [Algorithmic Monoculture and Social Welfare](https://mlsanity.com/paper/2101.05853/) (2021)
- [Trading Off Diversity and Quality in Natural Language Generation](https://mlsanity.com/paper/2004.10450/) (2020)
- [Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?](https://mlsanity.com/paper/2211.13972/) (2022)
- [On Decoding Strategies for Neural Text Generators](https://mlsanity.com/paper/2203.15721/) (2022)
- [Controlled Text Generation as Continuous Optimization with Multiple Constraints](https://mlsanity.com/paper/2108.01850/) (2021)
- [Preserving Diversity in Supervised Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2408.16673/) (2024)
- [Gradient-Based Constrained Sampling from Language Models](https://mlsanity.com/paper/2205.12558/) (2022)
- [Personas as a Way to Model Truthfulness in Language Models](https://mlsanity.com/paper/2310.18168/) (2023)
- [LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversity](https://mlsanity.com/paper/2410.03953/) (2024)
- [A Systematic Characterization of Sampling Algorithms for Open-ended Language Generation](https://mlsanity.com/paper/2009.07243/) (2020)
- [How Far Can We Extract Diverse Perspectives from Large Language Models?](https://mlsanity.com/paper/2311.09799/) (2023)
- [Explicit Diversity Conditions for Effective Question Answer Generation with Large Language Models](https://mlsanity.com/paper/2406.17990/) (2024)

## Built on by (most cited first, 9 of 9)

- [Jointly Reinforcing Diversity and Quality in Language Model Generations](https://mlsanity.com/paper/2509.02534/) (2025)
- [NoveltyBench: Evaluating Language Models for Humanlike Diversity](https://mlsanity.com/paper/2504.05228/) (2025)
- [Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards](https://mlsanity.com/paper/2509.24981/) (2025)
- [Learning to Explore with Parameter-Space Noise: A Deep Dive into Parameter-Space Noise for Reinforcement Learning with Verifiable Rewards](https://mlsanity.com/paper/2602.02555/) (2026)
- [The Basic B*** Effect: The Use of LLM-based Agents Reduces the Distinctiveness and Diversity of People's Choices](https://mlsanity.com/paper/2509.02910/) (2025)
- [Geometry of Knowledge Allows Extending Diversity Boundaries of Large Language Models](https://mlsanity.com/paper/2507.13874/) (2025)
- [UpSkill: Mutual Information Skill Learning for Structured Response Diversity in LLMs](https://mlsanity.com/paper/2602.22296/) (2026)
- [PLURAL: A Global Dataset for Value Alignment](https://mlsanity.com/paper/2607.08034/) (2026)
- [On Epistemic Diversity in Large Language Models](https://mlsanity.com/paper/2609.04835/) (2026)

## Abstract (arXiv)

How diverse are the outputs of large language models when diversity is desired? We examine the diversity of responses of several language models to questions with multiple possible answers, comparing them with human responses. Our findings suggest that models' responses are highly concentrated, reflecting narrow, mainstream outputs, in comparison to humans, whose responses exhibit a much longer-tail. We examine three simple and practical ways to increase output diversity: 1) increasing generation randomness via temperature sampling; 2) prompting models to answer from diverse perspectives using a single prompt; 3) aggregating outputs from several models. We find that these interventions, especially when combined, can substantially increase output diversity, although single-model outputs generally remain less diverse than the human baseline. We discuss potential implications of these findings for future work in AI policy and governance that wishes to preserve cultural diversity, an essential building block of a democratic social fabric.