mlsanityData to 14 Oct 2026

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

arXiv 2407.12856 ↗First posted 9 Jul 2024cs.CL cs.AI cs.CYcited by 26

Not on the map. Why?

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.

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

3 of 26 references.

References · 3

  1. 2023Steering Llama 2 via Contrastive Activation Additioncited by 1,085
  2. 2023Gender bias and stereotypes in Large Language Modelscited by 187
  3. 2019ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networkscited by 73

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 7; 2026: 17.

26 papers.

Sort:

By area:

  1. 2024The Moral Turing Test: Evaluating Human-LLM Alignment in Moral Decision-Makingcited by 12
  2. 2025Evaluating LLM Agent Collusion in Double Auctionscited by 11
  3. 2025The Multilingual Divide and Its Impact on Global AI Safetycited by 10
  4. 2026Conformity Dynamics in LLM Multi-Agent Systems: The Roles of Topology and Self-Social Weightingcited by 10
  5. 2026Learn-to-Distance: Distance Learning for Detecting LLM-Generated Textcited by 8
  6. 2026How are AI agents used? Evidence from 177,000 MCP toolscited by 7
  7. 2025Pencils to Pixels: A Systematic Study of Creative Drawings across Children, Adults and AIcited by 6
  8. 2026Do LLMs Favor LLMs? Quantifying Interaction Effects in Peer Reviewcited by 3
  9. 2026Architecting Trust in Artificial Epistemic Agentscited by 3
  10. 2026Label Effects: Shared Heuristic Reliance in Trust Assessment by Humans and LLM-as-a-Judgecited by 3
  11. 2026Why Do LLMs Struggle in Strategic Play? Broken Links Between Observations, Beliefs, and Actionscited by 3
  12. 2024Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systemscited by 2
14 more
  1. 2025Bias Beneath the Tone: Empirical Characterisation of Tone Bias in LLM-Driven UX Systemscited by 1
  2. 2026MLLM-as-a-Judge Exhibits Model Preference Biascited by 1
  3. 2026On the impact of retrieved content representations in RAG Pipelinescited by 1
  4. 2026Who Flips? Self- and Cross-Model Counterarguments Reveal Answer Instability in LLMscited by 1
  5. 2026LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systemscited by 1
  6. 2025CogniAlign: Survivability-Grounded Multi-Agent Moral Reasoning for Safe and Transparent AIcited by 0
  7. 2025CLINB: A Climate Intelligence Benchmark for Foundational Modelscited by 0
  8. 2025A Multifaceted Analysis of Social Biases in Large Language Modelscited by 0
  9. 2026Pro-AI Bias in Large Language Modelscited by 0
  10. 2026LLM Nepotism in Organizational Governancecited by 0
  11. 2026Show, Don't TELL: Explainable AI-Generated Text Detectioncited by 0
  12. 2026Post-Training Recipe, More Than Model Family, Shapes Multi-Agent LLM Conversational Behaviorcited by 0
  13. 2026A Shared Taste for Model-Written Text: The Generator-by-Selector Matrices of "AI-AI Bias" Show No Detectable Own-Model Premiumcited by 0
  14. 2026Drivers of LLM Consensus Formation Under Competing Incentives: A Simulation Studycited by 0