The Personalization Trap: How User Memory Alters Emotional Reasoning in LLMs
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_ | 1866908587524096000 |
|---|---|
| author | Fang, Xi Xu, Weijie Zhang, Yuchong Eckman, Stephanie Nickleach, Scott Reddy, Chandan K. |
| author_facet | Fang, Xi Xu, Weijie Zhang, Yuchong Eckman, Stephanie Nickleach, Scott Reddy, Chandan K. |
| contents | When an AI assistant remembers that Sarah is a single mother working two jobs, does it interpret her stress differently than if she were a wealthy executive? As personalized AI systems increasingly incorporate long-term user memory, understanding how this memory shapes emotional reasoning is critical. We investigate how user memory affects emotional intelligence in large language models (LLMs) by evaluating 15 models on human validated emotional intelligence tests. We find that identical scenarios paired with different user profiles produce systematically divergent emotional interpretations. Across validated user independent emotional scenarios and diverse user profiles, systematic biases emerged in several high-performing LLMs where advantaged profiles received more accurate emotional interpretations. Moreover, LLMs demonstrate significant disparities across demographic factors in emotion understanding and supportive recommendations tasks, indicating that personalization mechanisms can embed social hierarchies into models emotional reasoning. These results highlight a key challenge for memory enhanced AI: systems designed for personalization may inadvertently reinforce social inequalities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_09905 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Personalization Trap: How User Memory Alters Emotional Reasoning in LLMs Fang, Xi Xu, Weijie Zhang, Yuchong Eckman, Stephanie Nickleach, Scott Reddy, Chandan K. Artificial Intelligence Computation and Language 68T50 I.2.7 When an AI assistant remembers that Sarah is a single mother working two jobs, does it interpret her stress differently than if she were a wealthy executive? As personalized AI systems increasingly incorporate long-term user memory, understanding how this memory shapes emotional reasoning is critical. We investigate how user memory affects emotional intelligence in large language models (LLMs) by evaluating 15 models on human validated emotional intelligence tests. We find that identical scenarios paired with different user profiles produce systematically divergent emotional interpretations. Across validated user independent emotional scenarios and diverse user profiles, systematic biases emerged in several high-performing LLMs where advantaged profiles received more accurate emotional interpretations. Moreover, LLMs demonstrate significant disparities across demographic factors in emotion understanding and supportive recommendations tasks, indicating that personalization mechanisms can embed social hierarchies into models emotional reasoning. These results highlight a key challenge for memory enhanced AI: systems designed for personalization may inadvertently reinforce social inequalities. |
| title | The Personalization Trap: How User Memory Alters Emotional Reasoning in LLMs |
| topic | Artificial Intelligence Computation and Language 68T50 I.2.7 |
| url | https://arxiv.org/abs/2510.09905 |