# Addressing LLM Diversity by Infusing Random Concepts

arXiv: https://arxiv.org/abs/2601.18053 · HTML: https://mlsanity.com/paper/2601.18053/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 16 references that are in the map.
- First posted on arXiv 26 Jan 2026.

## Builds on (most cited first, 9 of 9)

- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [Generative artificial intelligence enhances creativity but reduces the diversity of novel content](https://mlsanity.com/paper/2312.00506/) (2023)
- [Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventions](https://mlsanity.com/paper/2306.04140/) (2023)
- [Echoes in AI: Quantifying lack of plot diversity in LLM outputs](https://mlsanity.com/paper/2501.00273/) (2024)
- [Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Voting](https://mlsanity.com/paper/2310.16523/) (2023)
- [A Robot Walks into a Bar: Can Language Models Serve as Creativity Support Tools for Comedy? An Evaluation of LLMs' Humour Alignment with Comedians](https://mlsanity.com/paper/2405.20956/) (2024)
- [Multilingual Prompting for Improving LLM Generation Diversity](https://mlsanity.com/paper/2505.15229/) (2025)
- [Image Generation Diversity Issues and How to Tame Them](https://mlsanity.com/paper/2411.16171/) (2024)

## Built on by (most cited first, 3 of 3)

- [Where You Inject Diversity Matters: A Unified Framework for Diverse Generation](https://mlsanity.com/paper/2606.10302/) (2026)
- [Probing an Embodied LLM: When Higher Observation Fidelity Hurts Problem Solving](https://mlsanity.com/paper/2605.20072/) (2026)
- [LLM Jaggedness Unlocks Scientific Creativity](https://mlsanity.com/paper/2605.10574/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are known to produce outputs with limited diversity. In this work, we study whether infusing random concepts in the prompts can improve the diversity of the generated outputs. To benchmark the approach, we design a systematic evaluation protocol which involves prompting an LLM with questions of the form "Name 10 Hollywood actors", and analyzing diversity measures of the resulting LLM outputs. Our experiments on multiple LLMs show that prepending random words/sentences unrelated to the prompt result in greater diversity in the outputs of LLMs. We believe that this promising result and the evaluation protocol opens up interesting avenues for future work, such as how infusing randomness into LLMs could be applied to other domains. Further, the evaluation protocol could also inspire research into benchmarking LLM diversity more systematically.