165 citations · 420 across the 25 of their papers we have counts for
26 papers
Prompt2Model: Generating Deployable Models from Natural Language Instructions
Vijay Viswanathan, Chenyang Zhao, Amanda Bertsch +2
Large language models (LLMs) enable system builders today to create competent NLP systems through prompting, where they only need to describe the task in natural language and provi…
Large Language Models Enable Few-Shot Clustering
Vijay Viswanathan, Kiril Gashteovski, Carolin Lawrence +2
Unlike traditional unsupervised clustering, semi-supervised clustering allows users to provide meaningful structure to the data, which helps the clustering algorithm to match the u…
LLMs as Workers in Human-Computational Algorithms? Replicating Crowdsourcing Pipelines with LLMs
Tongshuang Wu, Haiyi Zhu, Maya Albayrak +21
LLMs have shown promise in replicating human-like behavior in crowdsourcing tasks that were previously thought to be exclusive to human abilities. However, current efforts focus ma…
Is AI the better programming partner? Human-Human Pair Programming vs. Human-AI pAIr Programming
Qianou Ma, Tongshuang Wu, Kenneth Koedinger
The emergence of large-language models (LLMs) that excel at code generation and commercial products such as GitHub's Copilot has sparked interest in human-AI pair programming (refe…
DataFinder: Scientific Dataset Recommendation from Natural Language Descriptions
Vijay Viswanathan, Luyu Gao, Tongshuang Wu +2
Modern machine learning relies on datasets to develop and validate research ideas. Given the growth of publicly available data, finding the right dataset to use is increasingly dif…
Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation
Patrick Fernandes, Aman Madaan, Emmy Liu +8
Many recent advances in natural language generation have been fueled by training large language models on internet-scale data. However, this paradigm can lead to models that genera…
Seeing Seeds Beyond Weeds: Green Teaming Generative AI for Beneficial Uses
Logan Stapleton, Jordan Taylor, Sarah Fox +2
Large generative AI models (GMs) like GPT and DALL-E are trained to generate content for general, wide-ranging purposes. GM content filters are generalized to filter out content wh…
ConvXAI: Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific Writing
Hua Shen, Chieh-Yang Huang, Tongshuang Wu +1
Despite a surge collection of XAI methods, users still struggle to obtain required AI explanations. Previous research suggests chatbots as dynamic solutions, but the effective desi…
Parachute: Evaluating Interactive Human-LM Co-writing Systems
Hua Shen, Tongshuang Wu
A surge of advances in language models (LMs) has led to significant interest in using LMs to build co-writing systems, in which humans and LMs interactively contribute to a shared…
ScatterShot: Interactive In-context Example Curation for Text Transformation
Tongshuang Wu, Hua Shen, Daniel S. Weld +2
The in-context learning capabilities of LLMs like GPT-3 allow annotators to customize an LLM to their specific tasks with a small number of examples. However, users tend to include…
Decisions that Explain Themselves: A User-Centric Deep Reinforcement Learning Explanation System
Xiaoran Wu, Zihan Yan, Chongjie Zhang +1
With deep reinforcement learning (RL) systems like autonomous driving being wildly deployed but remaining largely opaque, developers frequently use explainable RL (XRL) tools to be…
Capabilities for Better ML Engineering
Chenyang Yang, Rachel Brower-Sinning, Grace A. Lewis +2
In spite of machine learning's rapid growth, its engineering support is scattered in many forms, and tends to favor certain engineering stages, stakeholders, and evaluation prefere…
Towards Natural Language-Based Visualization Authoring
Yun Wang, Zhitao Hou, Leixian Shen +5
A key challenge to visualization authoring is the process of getting familiar with the complex user interfaces of authoring tools. Natural Language Interface (NLI) presents promisi…
Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension
Ying Xu, Dakuo Wang, Mo Yu +15
Question answering (QA) is a fundamental means to facilitate assessment and training of narrative comprehension skills for both machines and young children, yet there is scarcity o…
Are Shortest Rationales the Best Explanations for Human Understanding?
Hua Shen, Tongshuang Wu, Wenbo Guo +1
Existing self-explaining models typically favor extracting the shortest possible rationales - snippets of an input text "responsible for" corresponding output - to explain the mode…
StoryBuddy: A Human-AI Collaborative Chatbot for Parent-Child Interactive Storytelling with Flexible Parental Involvement
Zheng Zhang, Ying Xu, Yanhao Wang +6
Despite its benefits for children's skill development and parent-child bonding, many parents do not often engage in interactive storytelling by having story-related dialogues with…
PromptChainer: Chaining Large Language Model Prompts through Visual Programming
Tongshuang Wu, Ellen Jiang, Aaron Donsbach +4
While LLMs can effectively help prototype single ML functionalities, many real-world applications involve complex tasks that cannot be easily handled via a single run of an LLM. Re…
Pretty Princess vs. Successful Leader: Gender Roles in Greeting Card Messages
Jiao Sun, Tongshuang Wu, Yue Jiang +3
People write personalized greeting cards on various occasions. While prior work has studied gender roles in greeting card messages, systematic analysis at scale and tools for raisi…
NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation
Kaustubh D. Dhole, Varun Gangal, Sebastian Gehrmann +122
Data augmentation is an important component in the robustness evaluation of models in natural language processing (NLP) and in enhancing the diversity of the data they are trained…
AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts
Tongshuang Wu, Michael Terry, Carrie J. Cai
Although large language models (LLMs) have demonstrated impressive potential on simple tasks, their breadth of scope, lack of transparency, and insufficient controllability can mak…
It is AI's Turn to Ask Humans a Question: Question-Answer Pair Generation for Children's Story Books
Bingsheng Yao, Dakuo Wang, Tongshuang Wu +4
Existing question answering (QA) techniques are created mainly to answer questions asked by humans. But in educational applications, teachers often need to decide what questions th…
DeHumor: Visual Analytics for Decomposing Humor
Xingbo Wang, Yao Ming, Tongshuang Wu +3
Despite being a critical communication skill, grasping humor is challenging -- a successful use of humor requires a mixture of both engaging content build-up and an appropriate voc…
Tailor: Generating and Perturbing Text with Semantic Controls
Alexis Ross, Tongshuang Wu, Hao Peng +2
Controlled text perturbation is useful for evaluating and improving model generalizability. However, current techniques rely on training a model for every target perturbation, whic…
Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models
Tongshuang Wu, Marco Tulio Ribeiro, Jeffrey Heer +1
While counterfactual examples are useful for analysis and training of NLP models, current generation methods either rely on manual labor to create very few counterfactuals, or only…