# Quantifying Cognitive Bias Induction in LLM-Generated Content

arXiv: https://arxiv.org/abs/2507.03194 · HTML: https://mlsanity.com/paper/2507.03194/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 56 references that are in the map.
- First posted on arXiv 3 Jul 2025.

## Builds on (most cited first, 30 of 31)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [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)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [Large Language Models Are Not Robust Multiple Choice Selectors](https://mlsanity.com/paper/2309.03882/) (2023)
- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP](https://mlsanity.com/paper/2103.00453/) (2021)
- [Towards Understanding and Mitigating Social Biases in Language Models](https://mlsanity.com/paper/2106.13219/) (2021)
- [Sentiment Analysis in the Era of Large Language Models: A Reality Check](https://mlsanity.com/paper/2305.15005/) (2023)
- [Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders](https://mlsanity.com/paper/2403.03952/) (2024)
- [Pre-Trained Language Models for Interactive Decision-Making](https://mlsanity.com/paper/2202.01771/) (2022)
- [Hierarchical Transformers for Multi-Document Summarization](https://mlsanity.com/paper/1905.13164/) (2019)
- [Cognitive Bias in Decision-Making with LLMs](https://mlsanity.com/paper/2403.00811/) (2024)
- [MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization](https://mlsanity.com/paper/2103.06410/) (2021)
- [Capturing Failures of Large Language Models via Human Cognitive Biases](https://mlsanity.com/paper/2202.12299/) (2022)
- [Attention Sorting Combats Recency Bias In Long Context Language Models](https://mlsanity.com/paper/2310.01427/) (2023)
- [Supporting Human-AI Collaboration in Auditing LLMs with LLMs](https://mlsanity.com/paper/2304.09991/) (2023)
- [Primacy Effect of ChatGPT](https://mlsanity.com/paper/2310.13206/) (2023)
- [Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding](https://mlsanity.com/paper/2109.11708/) (2021)
- [On Positional Bias of Faithfulness for Long-form Summarization](https://mlsanity.com/paper/2410.23609/) (2024)
- [This is not correct! Negation-aware Evaluation of Language Generation Systems](https://mlsanity.com/paper/2307.13989/) (2023)
- [The LLM Effect: Are Humans Truly Using LLMs, or Are They Being Influenced By Them Instead?](https://mlsanity.com/paper/2410.04699/) (2024)
- [Despite "super-human" performance, current LLMs are unsuited for decisions about ethics and safety](https://mlsanity.com/paper/2212.06295/) (2022)
- [Exploring the Cognitive Knowledge Structure of Large Language Models: An Educational Diagnostic Assessment Approach](https://mlsanity.com/paper/2310.08172/) (2023)
- [Mitigating Biases in Collective Decision-Making: Enhancing Performance in the Face of Fake News](https://mlsanity.com/paper/2403.08829/) (2024)

## Built on by (most cited first, 7 of 7)

- [When Summaries Distort Decisions: Information Fidelity in LLM-Compressed Financial Analysis](https://mlsanity.com/paper/2606.29251/) (2026)
- [CogManip: Benchmarking Manipulative Behavior in Multi-Turn Interactions with Large Language Model](https://mlsanity.com/paper/2606.06099/) (2026)
- [Contaminated Collaboration: Measuring Gender Bias Transfer in LLM-Assisted Student Writing](https://mlsanity.com/paper/2606.15914/) (2026)
- [AI-accelerated End-to-End Framework for Rapid Professional Upskilling](https://mlsanity.com/paper/2607.14044/) (2026)
- [Symphony of Bias: Exploring Gender Associations with Musical Instruments in Multimodal LLMs](https://mlsanity.com/paper/2607.26355/) (2026)
- [Who Verifies the Benchmark? Decentralizing Trust in Large Language Model Evaluation](https://mlsanity.com/paper/2608.07762/) (2026)
- [Knowing Is Not Telling: Identity Ossification in LLM Representations of Trans-border Communities](https://mlsanity.com/paper/2610.12610/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are integrated into applications like shopping reviews, summarization, or medical diagnosis support, where their use affects human decisions. We investigate the extent to which LLMs expose users to biased content and demonstrate its effect on human decision-making. We assess five LLM families in summarization and news fact-checking tasks, evaluating the consistency of LLMs with their context and their tendency to hallucinate on a new self-updating dataset. Our findings show that LLMs expose users to content that changes the context's sentiment in 26.42% of cases (framing bias), hallucinate on 60.33% of post-knowledge-cutoff questions, and highlight context from earlier parts of the prompt (primacy bias) in 10.12% of cases, averaged across all tested models. We further find that humans are 32% more likely to purchase the same product after reading a summary of the review generated by an LLM rather than the original review. To address these issues, we evaluate 18 mitigation methods across three LLM families and find the effectiveness of targeted interventions.