# Pro-AI Bias in Large Language Models

arXiv: https://arxiv.org/abs/2601.13749 · HTML: https://mlsanity.com/paper/2601.13749/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 45 references that are in the map.
- First posted on arXiv 20 Jan 2026.

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

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders](https://mlsanity.com/paper/2404.05961/) (2024)
- [On Measuring Social Biases in Sentence Encoders](https://mlsanity.com/paper/1903.10561/) (2019)
- [State of What Art? A Call for Multi-Prompt LLM Evaluation](https://mlsanity.com/paper/2401.00595/) (2023)
- [Benchmarking Cognitive Biases in Large Language Models as Evaluators](https://mlsanity.com/paper/2309.17012/) (2023)
- [Generative Language Models Exhibit Social Identity Biases](https://mlsanity.com/paper/2310.15819/) (2023)
- [Bias in Large Language Models: Origin, Evaluation, and Mitigation](https://mlsanity.com/paper/2411.10915/) (2024)
- [Efficient multi-prompt evaluation of LLMs](https://mlsanity.com/paper/2405.17202/) (2024)
- [Repetition Improves Language Model Embeddings](https://mlsanity.com/paper/2402.15449/) (2024)
- [Evaluating the Zero-shot Robustness of Instruction-tuned Language Models](https://mlsanity.com/paper/2306.11270/) (2023)
- [Improving zero-shot learning by mitigating the hubness problem](https://mlsanity.com/paper/1412.6568/) (2014)
- [Decision-Oriented Dialogue for Human-AI Collaboration](https://mlsanity.com/paper/2305.20076/) (2023)
- [Large Language Models as Recommender Systems: A Study of Popularity Bias](https://mlsanity.com/paper/2406.01285/) (2024)
- [AI-AI Bias: large language models favor communications generated by large language models](https://mlsanity.com/paper/2407.12856/) (2024)
- [Auditing the Use of Language Models to Guide Hiring Decisions](https://mlsanity.com/paper/2404.03086/) (2024)
- [Are Generative AI Agents Effective Personalized Financial Advisors?](https://mlsanity.com/paper/2504.05862/) (2025)
- [Rankers, Judges, and Assistants: Towards Understanding the Interplay of LLMs in Information Retrieval Evaluation](https://mlsanity.com/paper/2503.19092/) (2025)
- [Taxonomy of User Needs and Actions](https://mlsanity.com/paper/2510.06124/) (2025)
- [Cognitive Effects in Large Language Models](https://mlsanity.com/paper/2308.14337/) (2023)
- [AdvisorQA: Towards Helpful and Harmless Advice-seeking Question Answering with Collective Intelligence](https://mlsanity.com/paper/2404.11826/) (2024)
- [HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants](https://mlsanity.com/paper/2509.08494/) (2025)
- [Measuring Political Preferences in AI Systems: An Integrative Approach](https://mlsanity.com/paper/2503.10649/) (2025)
- [Evaluate Bias without Manual Test Sets: A Concept Representation Perspective for LLMs](https://mlsanity.com/paper/2505.15524/) (2025)
- [Gender and Positional Biases in LLM-Based Hiring Decisions: Evidence from Comparative CV/R'esum'e Evaluations](https://mlsanity.com/paper/2505.17049/) (2025)
- [Out-of-Context Reasoning in Large Language Models](https://mlsanity.com/paper/2503.10408/) (2025)
- [Towards New Benchmark for AI Alignment & Sentiment Analysis in Socially Important Issues: A Comparative Study of Human and LLMs in the Context of AGI](https://mlsanity.com/paper/2501.02531/) (2025)

## Abstract (arXiv)

Large language models (LLMs) are increasingly employed for decision-support across multiple domains. We investigate whether these models display a systematic preferential bias in favor of artificial intelligence (AI) itself. Across three complementary experiments, we find consistent evidence of pro-AI bias. First, we show that LLMs disproportionately recommend AI-related options in response to diverse advice-seeking queries, with proprietary models doing so almost deterministically. Second, we demonstrate that models systematically overestimate salaries for AI-related jobs relative to closely matched non-AI jobs, with proprietary models overestimating AI salaries more by 10 percentage points. Finally, probing internal representations of open-weight models reveals that ``Artificial Intelligence'' exhibits the highest similarity to generic prompts for academic fields under positive, negative, and neutral framings alike, indicating valence-invariant representational centrality. These patterns suggest that LLM-generated advice and valuation can systematically skew choices and perceptions in high-stakes decisions.