paper-with-me

Papers

The AI Memory Gap: Users Misremember What They Created With AI or Without

2025-09-15 · Tim Zindulka, Sven Goller, Daniela Fernandes, Robin Welsch, Daniel Buschek arxiv

As large language models (LLMs) become embedded in interactive text generation, disclosure of AI as a source depends on people remembering which ideas or texts came from themselves and which were created with AI. We investigate how accurately people remember the source of content when using AI. In a pre-registered experiment, 184 participants generated and elaborated on ideas both unaided and with an LLM-based chatbot. One week later, they were asked to identify the source (noAI vs withAI) of these ideas and texts. Our findings reveal a significant gap in memory: After AI use, the odds of correct attribution dropped, with the steepest decline in mixed human-AI workflows, where either the idea or elaboration was created with AI. We validated our results using a computational model of source memory. Discussing broader implications, we highlight the importance of considering source confusion in the design and use of interactive text generation technologies.

📄 PDF Abstract BibTeX arXiv:2509.11851

Code (0)

등록된 구현이 없습니다.

Tasks

Text Generation

Similar Papers 제목 키워드 기반

When Agents "Misremember" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems

2026-01-31 · Naen Xu, Hengyu An, Shuo Shi, Jinghuai Zhang 외 arxiv

Recent advancements in large language models (LLMs) have significantly enhanced the capabilities of collaborative multi-agent systems, enabling them to address complex challenges. However, within these multi-agent system…

“It’s our fault!”: Insights Into Users’ Understanding and Interaction With an Explanatory Collaborative Dialog System

2021-11-01 · CoNLL (EMNLP) 2021 11 · Katharina Weitz, Lindsey Vanderlyn, Ngoc Thang Vu, Elisabeth André

Human-AI collaboration, a long standing goal in AI, refers to a partnership where a human and artificial intelligence work together towards a shared goal. Collaborative dialog allows human-AI teams to communicate and lev…

Tell Me What To Learn: Generalizing Neural Memory to be Controllable in Natural Language

2026-02-26 · Max S. Bennett, Thomas P. Zollo, Richard Zemel arxiv

Modern machine learning models are deployed in diverse, non-stationary environments where they must continually adapt to new tasks and evolving knowledge. Continual fine-tuning and in-context learning are costly and brit…

Click-Through Rate Prediction with the User Memory Network

2019-07-09 · Wentao Ouyang, Xiuwu Zhang, Shukui Ren, Li Li 외

Click-through rate (CTR) prediction is a critical task in online advertising systems. Models like Deep Neural Networks (DNNs) are simple but stateless. They consider each target ad independently and cannot directly extra…

Click-Through Rate PredictionPrediction

Quantum Brain Dynamics. A Possibility of Having a Quantum Interpretation of the Brain

2023-06-05 · Dozie Iwuh

What Quantum Brain Dynamics (QBD) considers is not just these other functions of the brain, this is because they can be well analyzed with the workings of classical mechanics (even though they still play host to a quantu…