Hyo Jin (Gina) Do

📄"Highlight All the Phrases: Enhancing LLM Transparency through Visual Factuality Indicators"
👉 arxiv.org/pdf/2508.06846
We found that highlighting every phrase in a response using a color scale for its factuality estimate was the most preferred and trusted design.

📄 "Hide or Highlight: Understanding the Impact of Factuality Expression on User Trust"
👉 arxiv.org/pdf/2508.07095
We discovered that hiding content estimated to be less factual, either by removing it or replacing it with vague statements, can enhance user trust while maintaining perceived quality.

❣️ Shout out to my amazing co-authors:
Rachel Ostrand, @wernergeyer.bsky.social , @keerthi166.bsky.social, Dennis Wei, and Justin Weisz!

If you'll be at AIES, I would love to connect and chat more about our work! 🙌

🤔 How can we best communicate the factuality of an AI model's response?

I'm excited to share two papers that will be presented at the AIES conference next week, both answering this question. 💡

CHIWORK 2025 Workshop on Navigating Generative AI Disclosure, Ownership, and Accountability in… by Hyo Jin Do (IBM Research, US), Molly Q. Feldman (Oberlin College, US), Jessica He (IBM Research, US), Angel Hsing-Chi Hwang (University…

When and how should we acknowledge the use of Gen AI? At CHIWORK 2025, we hosted a workshop exploring these issues of AI disclosure, ownership, and accountability. Check out what we discussed in our Medium article!

LLM-as-a-Judge Without the Headaches: EvalAssist Brings Structure and Simplicity to the Chaos of LLM Output Review | AI Alliance Evaluating AI model outputs at scale is a major challenge for teams using LLMs, especially when assessing nuanced qualities like politeness, fairness, and tone that traditional benchmarks miss. IBM Re...

📣 Today we open-sourced EvalAssist, a web-based tool that makes it super easy to develop criteria for llm judges. You can run this now locally and then scale up with notebooks using Unitxt. Check out the AI Alliance article to get the scoop:
thealliance.ai/blog/llm-as-...

Interested in Navigating Generative AI Disclosure, Ownership, and Accountability in Co-Creative Domains? Our deadline is *extended* until May 7th AOE!

Come participate at our @chiwork.bsky.social workshop _in person_ in Amsterdam or _virtually_!

More info here: chiwork-aidisclosure.github.io

Image containing a call for participation for the workshop "Navigating Generative AI Disclosure, Ownership, and Accountability in Co-Creative Domains" at CHWORK 2025. Lists the problems and co-organizers. Submission deadline is April 24 2025 AOE and more information available at https://chiwork-aidisclosure.github.io/

Check out our upcoming workshop at CHIWORK 2025 (@chiwork.bsky.social): Navigating Generative AI Disclosure, Ownership, and Accountability in Co-Creative Domains.

CfP and more info at chiwork-aidisclosure.github.io