# Bias Beware: The Impact of Cognitive Biases on LLM-Driven Product Recommendations

arXiv: https://arxiv.org/abs/2502.01349 · HTML: https://mlsanity.com/paper/2502.01349/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 48 references that are in the map.
- First posted on arXiv 3 Feb 2025.

## Builds on (most cited first, 26 of 26)

- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge](https://mlsanity.com/paper/2410.02736/) (2024)
- [Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System](https://mlsanity.com/paper/2303.14524/) (2023)
- [Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders](https://mlsanity.com/paper/2403.03952/) (2024)
- [On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective](https://mlsanity.com/paper/2302.12095/) (2023)
- [Inverse Scaling: When Bigger Isn't Better](https://mlsanity.com/paper/2306.09479/) (2023)
- [Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks](https://mlsanity.com/paper/2310.10844/) (2023)
- [How Can Recommender Systems Benefit from Large Language Models: A Survey](https://mlsanity.com/paper/2306.05817/) (2023)
- [Weak-to-Strong Jailbreaking on Large Language Models](https://mlsanity.com/paper/2401.17256/) (2024)
- [Cognitive Bias in Decision-Making with LLMs](https://mlsanity.com/paper/2403.00811/) (2024)
- [GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretation](https://mlsanity.com/paper/2304.03879/) (2023)
- [Capturing Failures of Large Language Models via Human Cognitive Biases](https://mlsanity.com/paper/2202.12299/) (2022)
- [What Evidence Do Language Models Find Convincing?](https://mlsanity.com/paper/2402.11782/) (2024)
- [Evaluating the Instruction-Following Robustness of Large Language Models to Prompt Injection](https://mlsanity.com/paper/2308.10819/) (2023)
- [A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)](https://mlsanity.com/paper/2404.00579/) (2024)
- [Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation](https://mlsanity.com/paper/2405.20485/) (2024)
- [Large Language Models and Cognitive Science: A Comprehensive Review of Similarities, Differences, and Challenges](https://mlsanity.com/paper/2409.02387/) (2024)
- [Anchoring Bias in Large Language Models: An Experimental Study](https://mlsanity.com/paper/2412.06593/) (2024)
- [A Comprehensive Evaluation of Cognitive Biases in LLMs](https://mlsanity.com/paper/2410.15413/) (2024)
- [Are Large Language Models Really Robust to Word-Level Perturbations?](https://mlsanity.com/paper/2309.11166/) (2023)
- [AI Can Be Cognitively Biased: An Exploratory Study on Threshold Priming in LLM-Based Batch Relevance Assessment](https://mlsanity.com/paper/2409.16022/) (2024)
- [Cognitive Biases in Large Language Models: A Survey and Mitigation Experiments](https://mlsanity.com/paper/2412.00323/) (2024)
- [Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?](https://mlsanity.com/paper/2401.18070/) (2024)
- [Cognitive Biases in Large Language Models for News Recommendation](https://mlsanity.com/paper/2410.02897/) (2024)

## Built on by (most cited first, 11 of 11)

- [Belief in Authority: Impact of Authority in Multi-Agent Evaluation Framework](https://mlsanity.com/paper/2601.04790/) (2026)
- [Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems](https://mlsanity.com/paper/2606.17443/) (2026)
- [Generative AI Advertising as a Problem of Trustworthy Commercial Intervention](https://mlsanity.com/paper/2605.18673/) (2026)
- [AILS-NTUA at SemEval-2026 Task 10: Agentic LLMs for Psycholinguistic Marker Extraction and Conspiracy Endorsement Detection](https://mlsanity.com/paper/2603.04921/) (2026)
- [Agent-Facing Information Design in LLM Tool Registries](https://mlsanity.com/paper/2605.23916/) (2026)
- [The Injection Paradox: Brand-Level Suppression in Safety-Trained LLM Recommendations via RAG Context Injection](https://mlsanity.com/paper/2606.09204/) (2026)
- [The Safeguard Worked. Is the LLM System Safer?](https://mlsanity.com/paper/2609.00519/) (2026)
- [A Finger on the Scale: Covert Policy Steering through Agentic Skills](https://mlsanity.com/paper/2609.02564/) (2026)
- [PriceBench: A Diagnostic Benchmark for Price, Quality, and Brand Preferences in LLM Booking Agents](https://mlsanity.com/paper/2609.31468/) (2026)
- [Reading Too Much into Context: Passive Exposure Can Steer LLM Decisions](https://mlsanity.com/paper/2609.33065/) (2026)
- [Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It](https://mlsanity.com/paper/2610.03195/) (2026)

## Abstract (arXiv)

The advent of Large Language Models (LLMs) has revolutionized product recommenders, yet their susceptibility to adversarial manipulation poses critical challenges, particularly in real-world commercial applications. Our approach is the first one to tap into human psychological principles, seamlessly modifying product descriptions, making such manipulations hard to detect. In this work, we investigate cognitive biases as black-box adversarial strategies, drawing parallels between their effects on LLMs and human purchasing behavior. Through extensive evaluation across models of varying scale, we find that certain biases, such as social proof, consistently boost product recommendation rate and ranking, while others, like scarcity and exclusivity, surprisingly reduce visibility. Our results demonstrate that cognitive biases are deeply embedded in state-of-the-art LLMs, leading to highly unpredictable behavior in product recommendations and posing significant challenges for effective mitigation.