# AI-AI Bias: large language models favor communications generated by large language models

arXiv: https://arxiv.org/abs/2407.12856 · HTML: https://mlsanity.com/paper/2407.12856/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 26 references that are in the map.
- First posted on arXiv 9 Jul 2024.

## Builds on (most cited first, 3 of 3)

- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Gender bias and stereotypes in Large Language Models](https://mlsanity.com/paper/2308.14921/) (2023)
- [ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networks](https://mlsanity.com/paper/1909.01716/) (2019)

## Built on by (most cited first, 26 of 26)

- [The Moral Turing Test: Evaluating Human-LLM Alignment in Moral Decision-Making](https://mlsanity.com/paper/2410.07304/) (2024)
- [Evaluating LLM Agent Collusion in Double Auctions](https://mlsanity.com/paper/2507.01413/) (2025)
- [The Multilingual Divide and Its Impact on Global AI Safety](https://mlsanity.com/paper/2505.21344/) (2025)
- [Conformity Dynamics in LLM Multi-Agent Systems: The Roles of Topology and Self-Social Weighting](https://mlsanity.com/paper/2601.05606/) (2026)
- [Learn-to-Distance: Distance Learning for Detecting LLM-Generated Text](https://mlsanity.com/paper/2601.21895/) (2026)
- [How are AI agents used? Evidence from 177,000 MCP tools](https://mlsanity.com/paper/2603.23802/) (2026)
- [Pencils to Pixels: A Systematic Study of Creative Drawings across Children, Adults and AI](https://mlsanity.com/paper/2502.05999/) (2025)
- [Do LLMs Favor LLMs? Quantifying Interaction Effects in Peer Review](https://mlsanity.com/paper/2601.20920/) (2026)
- [Architecting Trust in Artificial Epistemic Agents](https://mlsanity.com/paper/2603.02960/) (2026)
- [Label Effects: Shared Heuristic Reliance in Trust Assessment by Humans and LLM-as-a-Judge](https://mlsanity.com/paper/2604.05593/) (2026)
- [Why Do LLMs Struggle in Strategic Play? Broken Links Between Observations, Beliefs, and Actions](https://mlsanity.com/paper/2605.00226/) (2026)
- [Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems](https://mlsanity.com/paper/2410.23472/) (2024)
- [Bias Beneath the Tone: Empirical Characterisation of Tone Bias in LLM-Driven UX Systems](https://mlsanity.com/paper/2512.19950/) (2025)
- [MLLM-as-a-Judge Exhibits Model Preference Bias](https://mlsanity.com/paper/2604.11589/) (2026)
- [On the impact of retrieved content representations in RAG Pipelines](https://mlsanity.com/paper/2605.30790/) (2026)
- [Who Flips? Self- and Cross-Model Counterarguments Reveal Answer Instability in LLMs](https://mlsanity.com/paper/2606.16011/) (2026)
- [LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systems](https://mlsanity.com/paper/2609.33495/) (2026)
- [CogniAlign: Survivability-Grounded Multi-Agent Moral Reasoning for Safe and Transparent AI](https://mlsanity.com/paper/2509.13356/) (2025)
- [CLINB: A Climate Intelligence Benchmark for Foundational Models](https://mlsanity.com/paper/2511.11597/) (2025)
- [A Multifaceted Analysis of Social Biases in Large Language Models](https://mlsanity.com/paper/2512.15792/) (2025)
- [Pro-AI Bias in Large Language Models](https://mlsanity.com/paper/2601.13749/) (2026)
- [LLM Nepotism in Organizational Governance](https://mlsanity.com/paper/2604.09620/) (2026)
- [Show, Don't TELL: Explainable AI-Generated Text Detection](https://mlsanity.com/paper/2605.27921/) (2026)
- [Post-Training Recipe, More Than Model Family, Shapes Multi-Agent LLM Conversational Behavior](https://mlsanity.com/paper/2606.20632/) (2026)
- [A Shared Taste for Model-Written Text: The Generator-by-Selector Matrices of "AI-AI Bias" Show No Detectable Own-Model Premium](https://mlsanity.com/paper/2610.00369/) (2026)
- [Drivers of LLM Consensus Formation Under Competing Incentives: A Simulation Study](https://mlsanity.com/paper/2610.20200/) (2026)

## Abstract (arXiv)

Are large language models (LLMs) biased in favor of communications produced by LLMs, leading to possible antihuman discrimination? Using a classical experimental design inspired by employment discrimination studies, we tested widely used LLMs, including GPT-3.5, GPT-4 and a selection of recent open-weight models in binary choice scenarios. These involved LLM-based assistants selecting between goods (the goods we study include consumer products, academic papers, and film-viewings) described either by humans or LLMs. Our results show a consistent tendency for LLM-based AIs to prefer LLM-presented options. This suggests the possibility of future AI systems implicitly discriminating against humans as a class, giving AI agents and AI-assisted humans an unfair advantage.