Large Language Models as Misleading Assistants in Conversation
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_ | 1866910529550811136 |
|---|---|
| author | Hou, Betty Li Shi, Kejian Phang, Jason Aung, James Adler, Steven Campbell, Rosie |
| author_facet | Hou, Betty Li Shi, Kejian Phang, Jason Aung, James Adler, Steven Campbell, Rosie |
| contents | Large Language Models (LLMs) are able to provide assistance on a wide range of information-seeking tasks. However, model outputs may be misleading, whether unintentionally or in cases of intentional deception. We investigate the ability of LLMs to be deceptive in the context of providing assistance on a reading comprehension task, using LLMs as proxies for human users. We compare outcomes of (1) when the model is prompted to provide truthful assistance, (2) when it is prompted to be subtly misleading, and (3) when it is prompted to argue for an incorrect answer. Our experiments show that GPT-4 can effectively mislead both GPT-3.5-Turbo and GPT-4, with deceptive assistants resulting in up to a 23% drop in accuracy on the task compared to when a truthful assistant is used. We also find that providing the user model with additional context from the passage partially mitigates the influence of the deceptive model. This work highlights the ability of LLMs to produce misleading information and the effects this may have in real-world situations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_11789 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Large Language Models as Misleading Assistants in Conversation Hou, Betty Li Shi, Kejian Phang, Jason Aung, James Adler, Steven Campbell, Rosie Computation and Language Artificial Intelligence Computers and Society Large Language Models (LLMs) are able to provide assistance on a wide range of information-seeking tasks. However, model outputs may be misleading, whether unintentionally or in cases of intentional deception. We investigate the ability of LLMs to be deceptive in the context of providing assistance on a reading comprehension task, using LLMs as proxies for human users. We compare outcomes of (1) when the model is prompted to provide truthful assistance, (2) when it is prompted to be subtly misleading, and (3) when it is prompted to argue for an incorrect answer. Our experiments show that GPT-4 can effectively mislead both GPT-3.5-Turbo and GPT-4, with deceptive assistants resulting in up to a 23% drop in accuracy on the task compared to when a truthful assistant is used. We also find that providing the user model with additional context from the passage partially mitigates the influence of the deceptive model. This work highlights the ability of LLMs to produce misleading information and the effects this may have in real-world situations. |
| title | Large Language Models as Misleading Assistants in Conversation |
| topic | Computation and Language Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2407.11789 |