# A Comprehensive Analysis of Large Language Model Outputs: Similarity, Diversity, and Bias

arXiv: https://arxiv.org/abs/2505.09056 · HTML: https://mlsanity.com/paper/2505.09056/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 68 references that are in the map.
- First posted on arXiv 14 May 2025.

## Builds on (most cited first, 30 of 45)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Persistent Anti-Muslim Bias in Large Language Models](https://mlsanity.com/paper/2101.05783/) (2021)
- [Toxicity in ChatGPT: Analyzing Persona-assigned Language Models](https://mlsanity.com/paper/2304.05335/) (2023)
- [Explainability for Large Language Models: A Survey](https://mlsanity.com/paper/2309.01029/) (2023)
- [Hallucination is Inevitable: An Innate Limitation of Large Language Models](https://mlsanity.com/paper/2401.11817/) (2024)
- [Measuring Bias in Contextualized Word Representations](https://mlsanity.com/paper/1906.07337/) (2019)
- [Measuring and Reducing Gendered Correlations in Pre-trained Models](https://mlsanity.com/paper/2010.06032/) (2020)
- [Identifying and Reducing Gender Bias in Word-Level Language Models](https://mlsanity.com/paper/1904.03035/) (2019)
- [Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models](https://mlsanity.com/paper/2305.18189/) (2023)
- ["Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters](https://mlsanity.com/paper/2310.09219/) (2023)
- [Gender bias and stereotypes in Large Language Models](https://mlsanity.com/paper/2308.14921/) (2023)
- [Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do](https://mlsanity.com/paper/2103.11790/) (2021)
- [Beyond Memorization: Violating Privacy Via Inference with Large Language Models](https://mlsanity.com/paper/2310.07298/) (2023)
- ["I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Dataset](https://mlsanity.com/paper/2205.09209/) (2022)
- [In-Context Impersonation Reveals Large Language Models' Strengths and Biases](https://mlsanity.com/paper/2305.14930/) (2023)
- [Having Beer after Prayer? Measuring Cultural Bias in Large Language Models](https://mlsanity.com/paper/2305.14456/) (2023)
- [Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings](https://mlsanity.com/paper/1904.04047/) (2019)
- [Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models](https://mlsanity.com/paper/1909.11299/) (2019)
- [Understanding the Origins of Bias in Word Embeddings](https://mlsanity.com/paper/1810.03611/) (2018)
- [Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations](https://mlsanity.com/paper/2310.11207/) (2023)
- [Mitigating Language-Dependent Ethnic Bias in BERT](https://mlsanity.com/paper/2109.05704/) (2021)

## Built on by (most cited first, 10 of 10)

- [LLM-42: Enabling Determinism in LLM Inference with Verified Speculation](https://mlsanity.com/paper/2601.17768/) (2026)
- [Measuring the Gap Between Human and LLM Research Ideas](https://mlsanity.com/paper/2607.01233/) (2026)
- [Markovian Generation Chains in Large Language Models](https://mlsanity.com/paper/2603.11228/) (2026)
- [AudAgent: Automated Auditing of Privacy Policy Compliance in AI Agents](https://mlsanity.com/paper/2511.07441/) (2025)
- [Quantum Circuit Generation via test-time learning with large language models](https://mlsanity.com/paper/2602.03466/) (2026)
- [Ex Ante Evaluation of AI-Induced Idea Diversity Collapse](https://mlsanity.com/paper/2605.06540/) (2026)
- [Efficient Mixture-of-Agents Serving via Tree-Structured Routing, Adaptive Pruning, and Dependency-Aware Prefill-Decode Overlap](https://mlsanity.com/paper/2512.18126/) (2025)
- [Never say never: Exploring the effects of available knowledge on agent persuasiveness in controlled physiotherapy motivation dialogues](https://mlsanity.com/paper/2602.12924/) (2026)
- [First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows](https://mlsanity.com/paper/2604.18038/) (2026)
- [Teachy Mini: Development and Preliminary Evaluation of a Knowledge-Based Generative Social Robot for Higher Education](https://mlsanity.com/paper/2607.22345/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) represent a major step toward artificial general intelligence, significantly advancing our ability to interact with technology. While LLMs perform well on Natural Language Processing tasks -- such as translation, generation, code writing, and summarization -- questions remain about their output similarity, variability, and ethical implications. For instance, how similar are texts generated by the same model? How does this compare across different models? And which models best uphold ethical standards? To investigate, we used 5{,}000 prompts spanning diverse tasks like generation, explanation, and rewriting. This resulted in approximately 3 million texts from 12 LLMs, including proprietary and open-source systems from OpenAI, Google, Microsoft, Meta, and Mistral. Key findings include: (1) outputs from the same LLM are more similar to each other than to human-written texts; (2) models like WizardLM-2-8x22b generate highly similar outputs, while GPT-4 produces more varied responses; (3) LLM writing styles differ significantly, with Llama 3 and Mistral showing higher similarity, and GPT-4 standing out for distinctiveness; (4) differences in vocabulary and tone underscore the linguistic uniqueness of LLM-generated content; (5) some LLMs demonstrate greater gender balance and reduced bias. These results offer new insights into the behavior and diversity of LLM outputs, helping guide future development and ethical evaluation.