A Comprehensive Evaluation of Cognitive Biases in LLMs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917053009494016 |
|---|---|
| author | Malberg, Simon Poletukhin, Roman Schuster, Carolin M. Groh, Georg |
| author_facet | Malberg, Simon Poletukhin, Roman Schuster, Carolin M. Groh, Georg |
| contents | We present a large-scale evaluation of 30 cognitive biases in 20 state-of-the-art large language models (LLMs) under various decision-making scenarios. Our contributions include a novel general-purpose test framework for reliable and large-scale generation of tests for LLMs, a benchmark dataset with 30,000 tests for detecting cognitive biases in LLMs, and a comprehensive assessment of the biases found in the 20 evaluated LLMs. Our work confirms and broadens previous findings suggesting the presence of cognitive biases in LLMs by reporting evidence of all 30 tested biases in at least some of the 20 LLMs. We publish our framework code to encourage future research on biases in LLMs: https://github.com/simonmalberg/cognitive-biases-in-llms |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_15413 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Comprehensive Evaluation of Cognitive Biases in LLMs Malberg, Simon Poletukhin, Roman Schuster, Carolin M. Groh, Georg Computation and Language Artificial Intelligence We present a large-scale evaluation of 30 cognitive biases in 20 state-of-the-art large language models (LLMs) under various decision-making scenarios. Our contributions include a novel general-purpose test framework for reliable and large-scale generation of tests for LLMs, a benchmark dataset with 30,000 tests for detecting cognitive biases in LLMs, and a comprehensive assessment of the biases found in the 20 evaluated LLMs. Our work confirms and broadens previous findings suggesting the presence of cognitive biases in LLMs by reporting evidence of all 30 tested biases in at least some of the 20 LLMs. We publish our framework code to encourage future research on biases in LLMs: https://github.com/simonmalberg/cognitive-biases-in-llms |
| title | A Comprehensive Evaluation of Cognitive Biases in LLMs |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2410.15413 |