mlsanityData to 14 Oct 2026

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

arXiv 2502.01349 ↗First posted 3 Feb 2025cs.CLcited by 11

Not on the map. Why?

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.

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

26 of 48 references.

References · 26

  1. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,651
  2. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,443
  3. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,135
  4. 2024Justice or Prejudice? Quantifying Biases in LLM-as-a-Judgecited by 368
  5. 2023Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender Systemcited by 242
  6. 2024Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoderscited by 224
  7. 2023On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspectivecited by 211
  8. 2023Inverse Scaling: When Bigger Isn't Bettercited by 207
  9. 2023Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attackscited by 194
  10. 2023How Can Recommender Systems Benefit from Large Language Models: A Surveycited by 142
  11. 2024Weak-to-Strong Jailbreaking on Large Language Modelscited by 107
  12. 2024Cognitive Bias in Decision-Making with LLMscited by 106
14 more
  1. 2023GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretationcited by 103
  2. 2022Capturing Failures of Large Language Models via Human Cognitive Biasescited by 98
  3. 2024What Evidence Do Language Models Find Convincing?cited by 75
  4. 2023Evaluating the Instruction-Following Robustness of Large Language Models to Prompt Injectioncited by 59
  5. 2024A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)cited by 58
  6. 2024Phantom: General Backdoor Attacks on Retrieval Augmented Language Generationcited by 49
  7. 2024Large Language Models and Cognitive Science: A Comprehensive Review of Similarities, Differences, and Challengescited by 49
  8. 2024Anchoring Bias in Large Language Models: An Experimental Studycited by 37
  9. 2024A Comprehensive Evaluation of Cognitive Biases in LLMscited by 34
  10. 2023Are Large Language Models Really Robust to Word-Level Perturbations?cited by 32
  11. 2024AI Can Be Cognitively Biased: An Exploratory Study on Threshold Priming in LLM-Based Batch Relevance Assessmentcited by 20
  12. 2024Cognitive Biases in Large Language Models: A Survey and Mitigation Experimentscited by 20
  13. 2024Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?cited by 19
  14. 2024Cognitive Biases in Large Language Models for News Recommendationcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 11.

11 papers.

  1. 2026Belief in Authority: Impact of Authority in Multi-Agent Evaluation Frameworkcited by 6
  2. 2026Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systemscited by 3
  3. 2026Generative AI Advertising as a Problem of Trustworthy Commercial Interventioncited by 1
  4. 2026AILS-NTUA at SemEval-2026 Task 10: Agentic LLMs for Psycholinguistic Marker Extraction and Conspiracy Endorsement Detectioncited by 0
  5. 2026Agent-Facing Information Design in LLM Tool Registriescited by 0
  6. 2026The Injection Paradox: Brand-Level Suppression in Safety-Trained LLM Recommendations via RAG Context Injectioncited by 0
  7. 2026The Safeguard Worked. Is the LLM System Safer?cited by 0
  8. 2026A Finger on the Scale: Covert Policy Steering through Agentic Skillscited by 0
  9. 2026PriceBench: A Diagnostic Benchmark for Price, Quality, and Brand Preferences in LLM Booking Agentscited by 0
  10. 2026Reading Too Much into Context: Passive Exposure Can Steer LLM Decisionscited by 0
  11. 2026Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce Itcited by 0