Bias Beware: The Impact of Cognitive Biases on LLM-Driven Product Recommendations
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914106887372800 |
|---|---|
| author | Filandrianos, Giorgos Dimitriou, Angeliki Lymperaiou, Maria Thomas, Konstantinos Stamou, Giorgos |
| author_facet | Filandrianos, Giorgos Dimitriou, Angeliki Lymperaiou, Maria Thomas, Konstantinos Stamou, Giorgos |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_01349 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bias Beware: The Impact of Cognitive Biases on LLM-Driven Product Recommendations Filandrianos, Giorgos Dimitriou, Angeliki Lymperaiou, Maria Thomas, Konstantinos Stamou, Giorgos Computation and Language 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. |
| title | Bias Beware: The Impact of Cognitive Biases on LLM-Driven Product Recommendations |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2502.01349 |