In psychology , a hallucination is a false sensory perception in the absence of an external stimulus, as distinct from an illusion , which is a misperception of an external stimulus. Hallucinations may occur in any sensory modality - visual, auditory, olfactory, gustatory, tactile, or mixed.
목차 목차 관련 글 AI Hallucinations: A Misnomer Worth Clarifying 이 글을 인용: “하지만 AI는 "감각 경험"을 하지 않으며 "환각"을 부정적 의미로 사용하는 건 실제 환각을 겪고 있는 사람들에게 낙인을 찍는 부작용이 있음.” HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems 이 글을 인용: “Retrieval-Augmented Generation (RAG) has been shown to improve knowledge capabilities and alleviate the halluci…” 열린 도메인 환각 “Open-domain hallucination is a hallucination where a model confidently generates false information about the wo…” Siren's song in the AI ocean: A survey on hallucination in large language models 관련 절: 2.2. What is LLM hallucination Survey of hallucination in natural language generation “In this survey, we thus provide a broad overview of the research progress and challenges in the hallucination p…” A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions “Subsequently, we present a thorough overview of hallucination detection methods and benchmarks.” A comprehensive taxonomy of hallucinations in Large Language Models “Furthermore, the report examines cognitive and human factors influencing hallucination perception, surveys eval…” LLMs will always hallucinate, and we need to live with this “This work introduces the concept of Structural Hallucination as an intrinsic nature of these systems.” Why Language Models Hallucinate 관련 절: Post-training and hallucination Language Models Know More Than They Show: Exploring Hallucinations From the Model's Viewpoint “Large language models (LLMs) often produce errors, including factual inaccuracies, biases, and reasoning failur…” GPT-4 technical report 관련 절: Memo Hallucinating faces 주제어가 겹침 A Proposal for Safe and Hallucination-free Coding AI 관련 절: Preface Nested Learning: The Illusion of Deep Learning Architectures “In this paper, we present a new learning paradigm, called Nested Learning (NL), that coherently represents a mo…” The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity “Particularly concerning is the counterintuitive reduction in reasoning effort as problems approach critical com…” Training LLMs for Honesty via Confessions “To demonstrate the viability of our approach, we train GPT-5-Thinking to produce confessions, and we evaluate i…” AI 시대의 프로그래밍 교육 주제어가 겹침 AI와 언론 “2024-06-28 - The value of journalism must be established in the AI era” AI 지원 프로그래밍을 위한 새 실천법 관련 절: 언제 무엇을 AI에게 시킬지 판단하기