Open AccessPosted Content
AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts
Reads0
Chats0
TLDR
In this paper, the authors introduce the concept of Chain LLM steps together, where the output of one step becomes the input for the next, thus aggregating the gains per step.Abstract:
Although large language models (LLMs) have demonstrated impressive potential on simple tasks, their breadth of scope, lack of transparency, and insufficient controllability can make them less effective when assisting humans on more complex tasks. In response, we introduce the concept of Chaining LLM steps together, where the output of one step becomes the input for the next, thus aggregating the gains per step. We first define a set of LLM primitive operations useful for Chain construction, then present an interactive system where users can modify these Chains, along with their intermediate results, in a modular way. In a 20-person user study, we found that Chaining not only improved the quality of task outcomes, but also significantly enhanced system transparency, controllability, and sense of collaboration. Additionally, we saw that users developed new ways of interacting with LLMs through Chains: they leveraged sub-tasks to calibrate model expectations, compared and contrasted alternative strategies by observing parallel downstream effects, and debugged unexpected model outputs by "unit-testing" sub-components of a Chain. In two case studies, we further explore how LLM Chains may be used in future applications.read more
Citations
More filters
Proceedings ArticleDOI
Co-Writing Screenplays and Theatre Scripts with Language Models: Evaluation by Industry Professionals
TL;DR: The authors apply language models hierarchically, in a system called Dramatron, to generate coherent scripts and screenplays complete with title, characters, story beats, location descriptions, and dialogue.
Proceedings ArticleDOI
Why Johnny Can’t Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts
TL;DR: The authors explored whether non-AI-experts can successfully engage in "end-user prompt engineering" using a design probe, a prototype LLM-based chatbot design tool supporting development and systematic evaluation of prompting strategies.
Proceedings ArticleDOI
Enabling Conversational Interaction with Mobile UI using Large Language Models
Bryan Wang,Gang Li,Yang Li +2 more
TL;DR: This paper proposes a design space to categorize conversations between the user and the agent when collaboratively accomplishing mobile tasks, and designs prompting techniques to adapt an LLM to conversational tasks on mobile UIs.
Proceedings ArticleDOI
On the Design of AI-powered Code Assistants for Notebooks
TL;DR: In this paper , the authors investigate the potential of code assistants in computational notebooks by creating a design space (reified from a survey of extant tools) and through an interview-design study with 15 practicing data scientists.
Proceedings ArticleDOI
The Idea Machine: LLM-based Expansion, Rewriting, Combination, and Suggestion of Ideas
TL;DR: The Idea Machine is introduced, a creativity support tool that leverages large language models (LLMs) to empower people engaged in idea generation tasks and includes a number of affordances that can be used to enable various levels of automation and intelligent support.
References
More filters
Proceedings Article
Attention is All you Need
Ashish Vaswani,Noam Shazeer,Niki Parmar,Jakob Uszkoreit,Llion Jones,Aidan N. Gomez,Lukasz Kaiser,Illia Polosukhin +7 more
TL;DR: This paper proposed a simple network architecture based solely on an attention mechanism, dispensing with recurrence and convolutions entirely and achieved state-of-the-art performance on English-to-French translation.
Book
A technique for the measurement of attitudes
TL;DR: The instrument to be described here is not, however, indirect in the usual sense of the word; it does not seek responses to items apparently unrelated to the attitudes investigated, and seeks to measure prejudice in a manner less direct than is true of the usual prejudice scale.
Proceedings Article
Language Models are Few-Shot Learners
Tom B. Brown,Benjamin Mann,Nick Ryder,Melanie Subbiah,Jared Kaplan,Prafulla Dhariwal,Arvind Neelakantan,Pranav Shyam,Girish Sastry,Amanda Askell,Sandhini Agarwal,Ariel Herbert-Voss,Gretchen Krueger,Thomas Henighan,Rewon Child,Aditya Ramesh,Daniel M. Ziegler,Jeffrey Wu,Clemens Winter,Christopher Hesse,Mark Chen,Eric Sigler,Mateusz Litwin,Scott Gray,Benjamin Chess,Jack Clark,Christopher Berner,Samuel McCandlish,Alec Radford,Ilya Sutskever,Dario Amodei +30 more
TL;DR: GPT-3 achieves strong performance on many NLP datasets, including translation, question-answering, and cloze tasks, as well as several tasks that require on-the-fly reasoning or domain adaptation, such as unscrambling words, using a novel word in a sentence, or performing 3-digit arithmetic.
Posted Content
Exploring the limits of language modeling
TL;DR: This work explores recent advances in Recurrent Neural Networks for large scale Language Modeling, and extends current models to deal with two key challenges present in this task: corpora and vocabulary sizes, and complex, long term structure of language.
Proceedings ArticleDOI
Soylent: a word processor with a crowd inside
Michael S. Bernstein,Greg Little,Robert C. Miller,Björn Hartmann,Mark S. Ackerman,David R. Karger,David Crowell,Katrina Panovich +7 more
TL;DR: S soylent, a word processing interface that enables writers to call on Mechanical Turk workers to shorten, proofread, and otherwise edit parts of their documents on demand, and the Find-Fix-Verify crowd programming pattern, which splits tasks into a series of generation and review stages.