Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.17304 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913888788807680 |
|---|---|
| author | Chadimová, Milena Jurášek, Eduard Kliegr, Tomáš |
| author_facet | Chadimová, Milena Jurášek, Eduard Kliegr, Tomáš |
| contents | This paper introduces a novel method, referred to as "hashing", which involves masking potentially bias-inducing words in large language models (LLMs) with hash-like meaningless identifiers to reduce cognitive biases and reliance on external knowledge. The method was tested across three sets of experiments involving a total of 490 prompts. Statistical analysis using chi-square tests showed significant improvements in all tested scenarios, which covered LLama, ChatGPT, Copilot, Gemini and Mixtral models. In the first experiment, hashing decreased the fallacy rate in a modified version of the "Linda" problem aimed at evaluating susceptibility to cognitive biases. In the second experiment, it improved LLM results on the frequent itemset extraction task. In the third experiment, we found hashing is also effective when the Linda problem is presented in a tabular format rather than text, indicating that the technique works across various input representations. Overall, the method was shown to improve bias reduction and incorporation of external knowledge. Despite bias reduction, hallucination rates were inconsistently reduced across types of LLM models. These findings suggest that masking bias-inducing terms can improve LLM performance, although its effectiveness is model- and task-dependent. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_17304 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Meaningless is better: hashing bias-inducing words in LLM prompts improves performance in logical reasoning and statistical learning Chadimová, Milena Jurášek, Eduard Kliegr, Tomáš Computation and Language Artificial Intelligence This paper introduces a novel method, referred to as "hashing", which involves masking potentially bias-inducing words in large language models (LLMs) with hash-like meaningless identifiers to reduce cognitive biases and reliance on external knowledge. The method was tested across three sets of experiments involving a total of 490 prompts. Statistical analysis using chi-square tests showed significant improvements in all tested scenarios, which covered LLama, ChatGPT, Copilot, Gemini and Mixtral models. In the first experiment, hashing decreased the fallacy rate in a modified version of the "Linda" problem aimed at evaluating susceptibility to cognitive biases. In the second experiment, it improved LLM results on the frequent itemset extraction task. In the third experiment, we found hashing is also effective when the Linda problem is presented in a tabular format rather than text, indicating that the technique works across various input representations. Overall, the method was shown to improve bias reduction and incorporation of external knowledge. Despite bias reduction, hallucination rates were inconsistently reduced across types of LLM models. These findings suggest that masking bias-inducing terms can improve LLM performance, although its effectiveness is model- and task-dependent. |
| title | Meaningless is better: hashing bias-inducing words in LLM prompts improves performance in logical reasoning and statistical learning |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2411.17304 |