Co-writing with opinionated language models affects users' views

M Jakesch, A Bhat, D Buschek, L Zalmanson… - Proceedings of the …, 2023 - dl.acm.org
If large language models like GPT-3 preferably produce a particular point of view, they may
influence people's opinions on an unknown scale. This study investigates whether a …

Lamp: When large language models meet personalization

A Salemi, S Mysore, M Bendersky, H Zamani - ar** a story, novices and published writers alike have had to look outside
themselves for inspiration. Language models have recently been able to generate text …

Choice over control: How users write with large language models using diegetic and non-diegetic prompting

H Dang, S Goller, F Lehmann, D Buschek - Proceedings of the 2023 CHI …, 2023 - dl.acm.org
We propose a conceptual perspective on prompts for Large Language Models (LLMs) that
distinguishes between (1) diegetic prompts (part of the narrative, eg “Once upon a time, I …

The value, benefits, and concerns of generative ai-powered assistance in writing

Z Li, C Liang, J Peng, M Yin - Proceedings of the 2024 CHI Conference …, 2024 - dl.acm.org
Recent advances in generative AI technologies like large language models raise both
excitement and concerns about the future of human-AI co-creation in writing. To unpack …

Optimization methods for personalizing large language models through retrieval augmentation

A Salemi, S Kallumadi, H Zamani - … of the 47th International ACM SIGIR …, 2024 - dl.acm.org
This paper studies retrieval-augmented approaches for personalizing large language
models (LLMs), which potentially have a substantial impact on various applications and …

The AI ghostwriter effect: When users do not perceive ownership of AI-generated text but self-declare as authors

F Draxler, A Werner, F Lehmann, M Hoppe… - ACM Transactions on …, 2024 - dl.acm.org
Human-AI interaction in text production increases complexity in authorship. In two empirical
studies (n1= 30 & n2= 96), we investigate authorship and ownership in human-AI …

The impact of multiple parallel phrase suggestions on email input and composition behaviour of native and non-native english writers

D Buschek, M Zürn, M Eiband - Proceedings of the 2021 CHI Conference …, 2021 - dl.acm.org
We present an in-depth analysis of the impact of multi-word suggestion choices from a
neural language model on user behaviour regarding input and text composition in email …

Integrating language models into classifiers for BCI communication: a review

W Speier, C Arnold, N Pouratian - Journal of neural engineering, 2016 - iopscience.iop.org
Objective. The present review systematically examines the integration of language models
to improve classifier performance in brain–computer interface (BCI) communication systems …