Publications (16)
Opal: Multimodal Image Generation for News Illustration
Vivian Liu, Han Qiao, Lydia Chilton
Advances in multimodal AI have presented people with powerful ways to create images from text. Recent work has shown that text-to-image generations are able to represent a broad ra…
The Labor Economics of Paid Crowdsourcing
John Horton, Lydia Chilton
Crowdsourcing is a form of "peer production" in which work traditionally performed by an employee is outsourced to an "undefined, generally large group of people in the form of an…
SafeText: A Benchmark for Exploring Physical Safety in Language Models
Sharon Levy, Emily Allaway, Melanie Subbiah +4
Understanding what constitutes safe text is an important issue in natural language processing and can often prevent the deployment of models deemed harmful and unsafe. One such typ…
Simulating Human Strategic Behavior: Comparing Single and Multi-agent LLMs
Karthik Sreedhar, Lydia Chilton
When creating policies, plans, or designs for people, it is challenging for designers to foresee all of the ways in which people may reason and behave. Recently, Large Language Mod…
STORYWARS: A Dataset and Instruction Tuning Baselines for Collaborative Story Understanding and Generation
Yulun Du, Lydia Chilton
Collaborative stories, which are texts created through the collaborative efforts of multiple authors with different writing styles and intentions, pose unique challenges for NLP mo…
Lightweight Decoding Strategies for Increasing Specificity
Katy Ilonka Gero, Chris Kedzie, Savvas Petridis +1
Language models are known to produce vague and generic outputs. We propose two unsupervised decoding strategies based on either word-frequency or point-wise mutual information to i…