Large Language Models as Misleading Assistants in Conversation
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy
Chaining Event Spans for Temporal Relation Grounding
CoMuMDR: Code-mixed Multi-modal Multi-domain corpus for Discourse paRsing in conversations
Automatic Generation of Inference Making Questions for Reading Comprehension Assessments
Dynamic Chunking and Selection for Reading Comprehension of Ultra-Long Context in Large Language Models
ReadBench: Measuring the Dense Text Visual Reading Ability of Vision-Language Models
토론
이 논문과 연결된 포럼 글이 아직 없습니다.