# Idiosyncrasies in Large Language Models

arXiv: https://arxiv.org/abs/2502.12150 · HTML: https://mlsanity.com/paper/2502.12150/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 83 references that are in the map.
- First posted on arXiv 17 Feb 2025.

## Builds on (most cited first, 30 of 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale](https://mlsanity.com/paper/2406.17557/) (2024)
- [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [Phi-4 Technical Report](https://mlsanity.com/paper/2412.08905/) (2024)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [GLTR: Statistical Detection and Visualization of Generated Text](https://mlsanity.com/paper/1906.04043/) (2019)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)
- [Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense](https://mlsanity.com/paper/2303.13408/) (2023)
- [How to Fine-Tune BERT for Text Classification?](https://mlsanity.com/paper/1905.05583/) (2019)
- [LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders](https://mlsanity.com/paper/2404.05961/) (2024)
- [Can AI-Generated Text be Reliably Detected?](https://mlsanity.com/paper/2303.11156/) (2023)
- [Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature](https://mlsanity.com/paper/2310.05130/) (2023)
- [Automatic Detection of Generated Text is Easiest when Humans are Fooled](https://mlsanity.com/paper/1911.00650/) (2019)
- [Automatic Detection of Machine Generated Text: A Critical Survey](https://mlsanity.com/paper/2011.01314/) (2020)
- [TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation](https://mlsanity.com/paper/2109.13296/) (2021)
- [A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions](https://mlsanity.com/paper/2310.14724/) (2023)
- [Describing Differences in Image Sets with Natural Language](https://mlsanity.com/paper/2312.02974/) (2023)
- [Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Edits](https://mlsanity.com/paper/2409.14509/) (2024)

## Built on by (most cited first, 30 of 33)

- [Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs](https://mlsanity.com/paper/2504.04715/) (2025)
- [What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts](https://mlsanity.com/paper/2505.13360/) (2025)
- [Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test](https://mlsanity.com/paper/2506.06975/) (2025)
- [Cost-Aware Contrastive Routing for LLMs](https://mlsanity.com/paper/2508.12491/) (2025)
- [SoK: Large Language Model Copyright Auditing via Fingerprinting](https://mlsanity.com/paper/2508.19843/) (2025)
- [Unified attacks to large language model watermarks: spoofing and scrubbing in unauthorized knowledge distillation](https://mlsanity.com/paper/2504.17480/) (2025)
- [Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs](https://mlsanity.com/paper/2506.14003/) (2025)
- [StoryScope: Investigating idiosyncrasies in AI fiction](https://mlsanity.com/paper/2604.03136/) (2026)
- [Natural Fingerprints of Large Language Models](https://mlsanity.com/paper/2504.14871/) (2025)
- [Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language Models](https://mlsanity.com/paper/2509.21155/) (2025)
- [One Token Is Enough: Fingerprinting and Verifying Large Language Models from Single-Token Output Distributions](https://mlsanity.com/paper/2607.10252/) (2026)
- [Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language Models](https://mlsanity.com/paper/2506.22957/) (2025)
- [Beyond One-Size-Fits-All: Inversion Learning for Highly Effective NLG Evaluation Prompts](https://mlsanity.com/paper/2504.21117/) (2025)
- [On the Detectability of LLM-Generated Text: What Exactly Is LLM-Generated Text?](https://mlsanity.com/paper/2510.20810/) (2025)
- [Why do AI agents communicate in human language?](https://mlsanity.com/paper/2506.02739/) (2025)
- [Asking Back: Interaction-Layer Antidistillation Watermarks](https://mlsanity.com/paper/2605.16462/) (2026)
- [Asymmetric Idiosyncrasies in Multimodal Models](https://mlsanity.com/paper/2602.22734/) (2026)
- [Machine individuality: Separating genuine idiosyncrasy from response bias in large language models](https://mlsanity.com/paper/2604.16755/) (2026)
- [Implicit Identity Technologies for LLMs: Fingerprinting and Watermarking across Datasets, Models, and Generated Content](https://mlsanity.com/paper/2605.29245/) (2026)
- [The Announcement Carries the Cue: Markup, Boundaries, and the Notation of Pre-Training Corpora](https://mlsanity.com/paper/2608.09093/) (2026)
- [Delta Activations: A Representation for Finetuned Large Language Models](https://mlsanity.com/paper/2509.04442/) (2025)
- [Feedback Forensics: A Toolkit to Measure AI Personality](https://mlsanity.com/paper/2509.26305/) (2025)
- [Discovering Implicit Large Language Model Alignment Objectives](https://mlsanity.com/paper/2602.15338/) (2026)
- [ACF: A Collaborative Framework for Agent Covert Communication under Cognitive Asymmetry](https://mlsanity.com/paper/2604.08276/) (2026)
- [Who Built This Model? Tracing LLM Lineage via Spectral Fingerprints in Weight Space](https://mlsanity.com/paper/2608.07786/) (2026)
- [Strangers to Themselves: What Language Models Say About Themselves Is Generic](https://mlsanity.com/paper/2609.09899/) (2026)
- [Prospective Interpretation Risk: Principled Communication Control Between LLMs](https://mlsanity.com/paper/2609.33885/) (2026)
- [PersMem: Internalizing Personality into Dual-Pathway Memory for LLM Agents](https://mlsanity.com/paper/2609.34372/) (2026)
- [Reach Into The CHOIR: Free-List Elicitation Uncovers Distinct Model Voices in LLM Ensembles](https://mlsanity.com/paper/2609.38448/) (2026)
- [You're Hired: Strategic Model Selection for LLM Collaboration](https://mlsanity.com/paper/2609.38816/) (2026)

## Abstract (arXiv)

In this work, we unveil and study idiosyncrasies in Large Language Models (LLMs) -- unique patterns in their outputs that can be used to distinguish the models. To do so, we consider a simple classification task: given a particular text output, the objective is to predict the source LLM that generates the text. We evaluate this synthetic task across various groups of LLMs and find that simply fine-tuning text embedding models on LLM-generated texts yields excellent classification accuracy. Notably, we achieve 97.1% accuracy on held-out validation data in the five-way classification problem involving ChatGPT, Claude, Grok, Gemini, and DeepSeek. Our further investigation reveals that these idiosyncrasies are rooted in word-level distributions. These patterns persist even when the texts are rewritten, translated, or summarized by an external LLM, suggesting that they are also encoded in the semantic content. Additionally, we leverage LLM as judges to generate detailed, open-ended descriptions of each model's idiosyncrasies. Finally, we discuss the broader implications of our findings, including training on synthetic data, inferring model similarity, and robust evaluation of LLMs. Code is available at https://github.com/locuslab/llm-idiosyncrasies.