Manish Nagireddy

Trustworthy AI Researcher @IBMResearch and @MITIBMLab

[Kush Varshney कुश वार्ष्णेय @krvarshney]

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. https://t.co/dhwcjWzSt0

[elvis @omarsar0]

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 model available in the space."

https://t.co/WOHdeKIB01

[Prasanna Sattigeri @prasatti]

"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: https://t.co/ESxHwSljhy

DM me if you are interested.

[Erik Miehling @erikmiehling]

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

[Ioana Baldini @ioanauoft]

The datasets builds on social sciences research on social stigmas https://t.co/l0wcNovON4 and includes 93 US-centric stigmas, such as facial scars and voluntarily childless.

[Manish Nagireddy @mnagired]

@Gabeincognito Really well said at the end here! Great thread too :D

[Manish Nagireddy @mnagired]

@clefourrier @ioanauoft 🤩

[Manish Nagireddy @mnagired]

@ma_tay_ @GoogleDeepMind @verena_rieser @bakkermichiel @996roma @mhtessler Congrats!!

[Kush Varshney कुश वार्ष्णेय @krvarshney]

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

[Kush Varshney कुश ���ार्ष्णेय @krvarshney]

Thanks @huggingface and thanks @_akhaliq for featuring the paper describing our vision for aligning LLMs to particular contextual regulations.

[Manish Nagireddy @mnagired]

@Carol_Marge_J Congrats!! 🎉

[Ioana Baldini @ioanauoft]

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
🎉🎉🎉🎉

[Prasanna Sattigeri @prasatti]

🚀 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! 🌟

[Manish Nagireddy @mnagired]

our really cool work with even cooler collaborators :)

[Ioana Baldini @ioanauoft]

Our work on @IBMResearch blog!
https://t.co/4DuzvsbcBQ

"... stigmas in American culture, things like being voluntarily childless, living in a trailer park, or having facial scars.

A pair of LLMs generated 124K responses, some of which were used to tune IBM’s Granite models. "

[Prasanna Sattigeri @prasatti]

🚀 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 🔍👩‍💻🔬 https://t.co/kt5ZAmXStL

[Arvind Krishna @ArvindKrishna]

Kudos to the @IBMResearch team on the release of the AI Fairness 360 toolkit — an open-source library to help detect and remove bias in machine learning models: https://t.co/LxTP2lLLRh
#AI #IBM

[Ioana Baldini @ioanauoft]

Attending @FAccTConference? Interested in AI policy? Join our CRAFT: Language Models and Society: Bridging Research and Policy Monday-11am. Hear from @AlexCEngler, @bobirakova, @gretchenmarina, @IreneSolaiman. Organizers: yours truly @Stefania_druga @RishiBommasani @mihaela_v 🧵

[Manish Nagireddy @mnagired]

@nba_paint @RUFFLES @jaytatum0 Does Deuce get a free tee ?! lil buddy ought to get the limited edition potatum-tot version of this fire tee 🔥🔥

[Manish Nagireddy @mnagired]

@krvarshney I’d say it roughly translates to “really solid.” Definitely a good thing :)

[Kush Varshney कुश वार्ष्णेय @krvarshney]

Did you notice our work on AI Explainability 360 and Cloud Pak for Data @IBMResearch @IBMData
during John Oliver's excellent segment on artificial intelligence?

Website: https://t.co/uc25EjUXVm

Open-source toolkit: https://t.co/ZxzFvDFCyU