CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities

• URL: http://arxiv.org/abs/2201.06796v1
• Date: Tue, 18 Jan 2022 07:51:57 GMT
• Title: CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities
• Authors: Mina Lee, Percy Liang, Qian Yang
• Abstract summary: We present CoAuthor, a dataset designed for revealing GPT-3's capabilities in assisting creative and argumentative writing. We demonstrate that CoAuthor can address questions about GPT-3's language, ideation, and collaboration capabilities. We discuss how this work may facilitate a more principled discussion around LMs' promises and pitfalls in relation to interaction design.
• Score: 92.79451009324268
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LMs) offer unprecedented language generation capabilities and exciting opportunities for interaction design. However, their highly context-dependent capabilities are difficult to grasp and are often subjectively interpreted. In this paper, we argue that by curating and analyzing large interaction datasets, the HCI community can foster more incisive examinations of LMs' generative capabilities. Exemplifying this approach, we present CoAuthor, a dataset designed for revealing GPT-3's capabilities in assisting creative and argumentative writing. CoAuthor captures rich interactions between 63 writers and four instances of GPT-3 across 1445 writing sessions. We demonstrate that CoAuthor can address questions about GPT-3's language, ideation, and collaboration capabilities, and reveal its contribution as a writing "collaborator" under various definitions of good collaboration. Finally, we discuss how this work may facilitate a more principled discussion around LMs' promises and pitfalls in relation to interaction design. The dataset and an interface for replaying the writing sessions are publicly available at https://coauthor.stanford.edu.

Related papers

• Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactions [62.0123588983514]
  Large Language Models (LLMs) have demonstrated wide-ranging applications across various fields. We reformulate the peer-review process as a multi-turn, long-context dialogue, incorporating distinct roles for authors, reviewers, and decision makers. We construct a comprehensive dataset containing over 26,841 papers with 92,017 reviews collected from multiple sources.
  arXiv  Detail & Related papers  (2024-06-09T08:24:17Z)
• Navigating the Path of Writing: Outline-guided Text Generation with Large Language Models [8.920436030483872]
  We propose Writing Path, a framework that uses explicit outlines to guide Large Language Models (LLMs) in generating user-aligned text. Our approach draws inspiration from structured writing planning and reasoning paths, focusing on capturing and reflecting user intentions throughout the writing process.
  arXiv  Detail & Related papers  (2024-04-22T06:57:43Z)
• Syntax and Semantics Meet in the "Middle": Probing the Syntax-Semantics Interface of LMs Through Agentivity [68.8204255655161]
  We present the semantic notion of agentivity as a case study for probing such interactions. This suggests LMs may potentially serve as more useful tools for linguistic annotation, theory testing, and discovery.
  arXiv  Detail & Related papers  (2023-05-29T16:24:01Z)
• Unraveling ChatGPT: A Critical Analysis of AI-Generated Goal-Oriented Dialogues and Annotations [1.7969777786551426]
  Large pre-trained language models have exhibited unprecedented capabilities in producing high-quality text via prompting. In this paper, we explore the potential of these models to generate and annotate goal-oriented dialogues, and conduct an in-depth analysis to evaluate their quality. Based on extensive human-based evaluations, we demonstrate that the quality of generated dialogues and annotations is on par with those generated by humans.
  arXiv  Detail & Related papers  (2023-05-23T22:31:01Z)
• SHINE: Syntax-augmented Hierarchical Interactive Encoder for Zero-shot Cross-lingual Information Extraction [47.88887327545667]
  In this study, a syntax-augmented hierarchical interactive encoder (SHINE) is proposed to transfer cross-lingual IE knowledge. SHINE is capable of interactively capturing complementary information between features and contextual information. Experiments across seven languages on three IE tasks and four benchmarks verify the effectiveness and generalization ability of the proposed method.
  arXiv  Detail & Related papers  (2023-05-21T08:02:06Z)
• Approach Intelligent Writing Assistants Usability with Seven Stages of Action [9.378355457555319]
  We adopt Norman's seven stages of action as a framework to approach the interaction design of intelligent writing assistants. We illustrate the framework's applicability to writing tasks by providing an example of software tutorial authoring.
  arXiv  Detail & Related papers  (2023-04-06T02:11:55Z)
• Large Language Models Meet Harry Potter: A Bilingual Dataset for Aligning Dialogue Agents with Characters [70.84938803753062]
  We introduce the Harry Potter Dialogue dataset, designed to advance the study of dialogue agents and character alignment. The dataset encompasses all dialogue sessions (in both English and Chinese) from the Harry Potter series. It is annotated with vital background information, including dialogue scenes, speakers, character relationships, and attributes.
  arXiv  Detail & Related papers  (2022-11-13T10:16:39Z)
• KETOD: Knowledge-Enriched Task-Oriented Dialogue [77.59814785157877]
  Existing studies in dialogue system research mostly treat task-oriented dialogue and chit-chat as separate domains. We investigate how task-oriented dialogue and knowledge-grounded chit-chat can be effectively integrated into a single model.
  arXiv  Detail & Related papers  (2022-05-11T16:01:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.