Kudos to the IBM Research team on the release of the AI Fairness 360 toolkit — an open-source library to help detect and remove bias in machine learning models: github.com/IBM/AIF360 #AI #IBM

We are proud of our Public Interest Technology Summer Fellows and their passion for public service work: citp.princeton.edu/citps-public-i…

All are welcome to join the AI Fairness 360 monthly bee. Second meeting on August 22 at 12 noon ET. Meeting link: tinyurl.com/aif360monthly #AIFairness360 #Fairness #trustworthy_ai

Last month, CITP’s Public Interest Technology Summer Fellowship participants met at Princeton University to share their experiences working at government agencies like the FTC, the @CFPB, and the office of Texas Attorney General. bit.ly/3pTPJYu

Here's a video of me describing AI Fairness 360, one of the winners of the Falling Walls Science and Innovation Management global call. falling-walls.com/discover/video…

Presenting a poster at ACM EAAMO (Handle Retired, Visit @EAAMO_ORG) this afternoon! Come chat about bias(stress)-testing fairness interventions and counterfactual bias injection if you’re around. Joint w/ Manish Nagireddy Logan Stapleton Hao-Fei Cheng Haiyi Zhu Steven Wu Hoda Heidari

Looking forward to giving my second lifetime talk at Carnegie Mellon on Monday at noon. My first time was in Kigali at Carnegie Mellon University Africa in September 2019. I'll be presenting a perspective on AI governance. cs.cmu.edu/calendar/16309…

Did you notice our work on AI Explainability 360 and Cloud Pak for Data IBM Research IBM Data, AI & Automation during John Oliver's excellent segment on artificial intelligence? Website: ibm.com/watson/explain… Open-source toolkit: aix360.mybluemix.net

Attending ACM FAccT? Interested in AI policy? Join our CRAFT: Language Models and Society: Bridging Research and Policy Monday-11am. Hear from Alex Engler, Bobi Rakova, @gretchenmarina, Irene Solaiman. Organizers: yours truly Stefania Druga rishi@NeurIPS Mickey Vorvoreanu (Dr. V) 🧵

🚀 Exciting Opportunity Alert! 🌟 Join our team as a Research Intern and contribute to the future of trustworthy foundation models. 🧠 Apply now to make a real impact! #AIResearch #InternshipOpportunity #FoundationModels 🔍👩‍💻🔬 careers.ibm.com/job/19183611

our really cool work with even cooler collaborators :)

🚀 Thread: Thrilled to share our latest work at #NeurIPS2023 I won't be there at the conference but here is what my amazing collaborators are presenting! 🌟

Come join us! I’ll present a sneak peak of our work on auditing LMs through stigma-based lens. We just received notification that the work was accepted to #AAAI2024 🎉🎉🎉🎉

Thanks Hugging Face and thanks AK for featuring the paper describing our vision for aligning LLMs to particular contextual regulations.

I wanted to share a bunch of ideas the human-centered and trustworthy AI teams at IBM Research labs worldwide have been simmering and are now externalizing. I encourage topics that might not be hyped, but are nevertheless important and ones that researchers believe in. /1

The datasets builds on social sciences research on social stigmas pubmed.ncbi.nlm.nih.gov/29290150/ and includes 93 US-centric stigmas, such as facial scars and voluntarily childless.

Pleased to announce that our recent paper on conversational maxims for human-AI interactions has been accepted to EMNLP 2024 Findings. 🧵

"Want to make AI safer? 🛡️ Join us through the Summer '25 internship program! Help level up our open-source models that keep AI honest and harmless. Granite-Guardian project is calling ✨ Apply now!" Link to apply: careers.ibm.com/job/21097301/2… DM me if you are interested.

IBM open-sources Granite Guardian, a suite of safeguards for risk detection in LLMs. The authors claim that "With AUC scores of 0.871 and 0.854 on harmful content and RAG-hallucination-related benchmarks respectively, Granite Guardian is the most generalizable and competitive

We released Granite Guardian 3.1 today! Even better at harm detection than Granite Guardian 3.0. The main new feature is 'function calling hallucination' detection relevant for tool-using AI agents. github.com/ibm-granite/gr…