Hi, I'm Savvas.

I am a visiting research scientist at Google PAIR (People + AI Research). I generally research Human-AI Interaction, with a focus on human interaction with LLMs and making LLMs easier to use.

I received my PhD in computer science (specialized in HCI, AI, and Human-AI Interaction) from Columbia University, where I was lucky to be advised by Prof. Lydia B. Chilton. I was also fortunate to have research internships at Spotify, Adobe, and IBM.

I'm on the job market for research scientist / engineer roles!

Feel free to reach out to me at: savvas@cs.columbia.edu

Selected Projects


ConstitutionalExperts: Training a Mixture of Principle-based Prompts

ConstitutionalExperts automatically improves LLM prompts via fine-grained principle edits. Unlike prior methods that optimize the prompt as a single entity, our method incrementally improves the prompt by surgically editing individual principles.

In submission at ACL 2024, [pdf]

ConstitutionMaker: Interactively Critiquing Large Language Models by Converting Feedback into Principles

ConstitutionMaker enables users to interactively improve LLM prompts with natural language feedback. Users can critique, kudos, or rewrite the LLM's output, and this feedback is then used to automatically update the prompt with a specific principle.

IUI 2024, [pdf]

PromptInfuser: How Tightly Coupling AI and UI Design Impacts Designers' Workflows

PromptInfuser is a Figma plugin that enables users to create functional medium-fidelity prototypes, by connecting the UI mockup to LLM prompts. In a study with 14 designers, we found that PromptInfuser encouraged iteration over prompt and UI together, which helped designers identify UI and prompt incompatibilities and reflect upon their total solution.

In submission at DIS 2024, [pdf]

AngleKindling: Supporting Journalistic Angle Ideation with Large Language Models

AngleKindling is an interactive web application which employs the common sense reasoning of LLMs to help journalists explore angles (e.g. controversies) for reporting on a press release. In a study with 12 professional journalists, we show that participants found AngleKindling signifcantly more helpful and less mentally demanding to use for brainstorming ideas, compared to a prior journalistic angle ideation tool.

CHI 2023, [pdf]

Publications

ConstitutionalExperts: Training a Mixture of Principle-based Prompts
Savvas Petridis*, Benjamin Wedin*, Ann Yuan*, James Wexler, Nithum Thain.
In submission at ACL 2024. * denotes equal contribution.

ConstitutionMaker: Interactively Critiquing Large Language Models by Converting Feedback into Principles
Savvas Petridis, Benjamin Wedin, James Wexler, Aaron Donsbach, Mahima Pushkarna, Nitesh Goyal, Carrie J. Cai, Michael Terry.
IUI 2024, ACM Conference on Intelligent User Interfaces.

PromptInfuser: How Tightly Coupling AI and UI Design Impacts Designers' Workflows
Savvas Petridis, Michael Terry, Carrie J. Cai.
In submission at DIS 2024.

Visualizing Linguistic Diversity of Text Datasets Synthesized by Large Language Models
Emily Reif, Minsuk Kahng, Savvas Petridis.
VIS 2023 (Short papers).

PromptInfuser: Bringing User Interface Mock-ups to Life with Large Language Models
Savvas Petridis, Michael Terry, Carrie J. Cai.
CHI 2023 Late Breaking Work, ACM Conference on Human Factors in Computing Systems.

AngleKindling: Supporting Journalistic Angle Ideation with Large Language Models
Savvas Petridis, Nicholas Diakopoulos, Kevin Crowston, Mark Hansen, Keren Henderson, Stan Jastrzebski, Jeffrey V. Nickerson, Lydia B. Chilton.
CHI 2023, ACM Conference on Human Factors in Computing Systems.

PopBlends: Strategies for Conceptual Blending with Large Language Models
Sitong Wang, Savvas Petridis, Taeahn Kwon, Xiaojuan Ma, Lydia B. Chilton.
CHI 2023, ACM Conference on Human Factors in Computing Systems.

TastePaths: Enabling Deeper Exploration and Understanding of Personal Preferences in Recommender Systems
Savvas Petridis, Nediyana Daskalova, Sarah Mennicken, Samuel F. Way, Paul Lamere, Jennifer Thom.
IUI 2022, ACM Conference on Intelligent User Interfaces.

SymbolFinder: Brainstorming Diverse Symbols Using Local Semantic Networks
Savvas Petridis, Hijung Valentina Shin, Lydia B. Chilton.
UIST 2021, ACM Symposium on User Interface Software and Technology.

Human Errors in Interpreting Visual Metaphor
Savvas Petridis and Lydia B. Chilton.
C&C 2019, ACM Conference on Creativity and Cognition.

VisiBlends: A Flexible Workflow for Visual Blends
Lydia B. Chilton, Savvas Petridis, Maneesh Agrawala.
CHI 2019, ACM Conference on Human Factors in Computing Systems.

Where is your Evidence: Improving Fact-checking by Justification
Tariq Alhindi, Savvas Petridis, Smaranda Muresan.
FEVER (Fact Extraction and Verification) Workshop at EMNLP 2018.

AMuSe: Large-scale WiFi video distribution - Experimentation on the ORBIT testbed
Varun Gupta, Raphael Norwitz, Savvas Petridis, Craig Gutterman, Gil Zussman, Yigal Bejerano.
Demo description in Proc. IEEE INFOCOM'16, 2016.

WiFi multicast to very large groups - experimentation on the ORBIT testbed
Varun Gupta, Raphael Norwitz, Savvas Petridis, Craig Gutterman, Gil Zussman, Yigal Bejerano.
Demo at IEEE LCN'15, 2015.