Shruthi Chari

ML Scientist - Bristol Myers Squibb | PhD - RPI | Applied Explainable AI. Pronouns: She/Her (Views are my own)

[Shruthi Chari @shruthichari]

Happy to share that version 2.0 of our Explanation Ontology has been accepted as a journal paper to the Special Issue in XAI at the Semantic Web Journal (SWJ). Link to paper: https://t.co/okrriZWbZz 1/6

[Shruthi Chari @shruthichari]

@vidhisha_b Very interesting work. Thanks for sharing.

[Shruthi Chari @shruthichari]

@_morgananna_ Same boat. Glad you decided to take it slower too Morgan. That last mile is hard -.-

[Shruthi Chari @shruthichari]

@oshaniws Many many congratulations Manan and Oshani :)

[Shruthi Chari @shruthichari]

Happy to share that I am now a PhD candidate and I am looking forward to a defense next year on my dissertation research titled, "An Ontology-Enabled Approach For User-Centered and Knowledge-Enabled Explanations of AI Systems" #phdlife @csatrpi

[Shruthi Chari @shruthichari]

@Sangha26Dutta Nice work an important step towards quantifying the quality of explanations.

[Shruthi Chari @shruthichari]

A really nice article in the WSJ today about the various use cases of AI in hospitals across the US: https://t.co/6oCsJZDzH3. It helps to both understand the trends of application of AI in healthcare and identify where we can improve. Thanks for sharing @dangruen.

[Shruthi Chari @shruthichari]

@UpolEhsan Also when do you RAI work, the typical question is do you program? I don’t see why most RAI projects which also often include a user study component are being considered non mainstream -,-

[Shruthi Chari @shruthichari]

Many congratulations to my advisor, Prof. Deborah McGuinness as being elected as a AAAI Fellow 2023!

[Deborah McGuinness @dlmcguinness]

Excited to share that the @RealAAAI fellows have been announced for this year and I am a recipient "for significant contributions to the semantic web, knowledge representation and reasoning environments, and deployed AI applications. @RPIScience @csatrpi @rpi

[Shruthi Chari @shruthichari]

Thanks to the efforts of all my collaborators and co-authors from @csatrpi and @IBMResearch - @oshaniws , @mo_ghalwash, @dangruen, Sola Shirai, @pchakrabt1, @jeriscience and @dlmcguinness. 6/6

[Shruthi Chari @shruthichari]

Happy to share that version 2.0 of our Explanation Ontology has been accepted as a journal paper to the Special Issue in XAI at the Semantic Web Journal (SWJ). Link to paper: https://t.co/okrriZWbZz 1/6

[Shruthi Chari @shruthichari]

You can download our ontology and explore our resource from our website: https://t.co/g5y0jaxqBS. Looking forward to feedback on using the EO or queries about applying it to your own use cases. 5/6

[Bojan Tunguz @tunguz]

.@Stanford’s PubMedGPT LLM passes US Medical Licensing Exam (MedQA-USMLE) with more than 50% correct answers. https://t.co/7rC3bPFG8O

[Shruthi Chari @shruthichari]

Nice thread on the shortcomings of LLMs and why we must build guards around them.

[Andrew Ng @AndrewYNg]

1/Large language models like Galactica and ChatGPT can spout nonsense in a confident, authoritative tone. This overconfidence - which reflects the data they’re trained on - makes them more likely to mislead.

[Shruthi Chari @shruthichari]

Never had a failed macOS upgrade before Ventura and it is painful to get your Mac to start again -.- Maybe finally a time where I appreciate more transparent options aka Linux.

[Read Raising Expectations (and Raising Hell) @JPHilllllll]

I can't believe in 2022 we're still sending reporters out in Hurricanes like this

[Shruthi Chari @shruthichari]

Hope such efforts bring to light the need to focus more on reporting results and releasing models more often outside of general-purpose domains. Also, hope that AI/ML papers start asking for more rigorous and illustrative analyses outside of just quantitative numbers. 2/2

[Shruthi Chari @shruthichari]

Happy to see an application of language models (LMs) in a high-stakes setting like the government. I like how the post author says it is to 'show, not tell' in this thread. Working on LMs, I was frustrated with how little there is outside of large corpora like Wikipedia. 1/2

[Jack Clark @jackclarkSF]

Today, I testified to the U.S. Senate Committee on Commerce, Science, & Transportation @commercedems. I used an @AnthropicAI language model to write the concluding part of my testimony. I believe this marks the first time a language model has 'testified' in the U.S. Senate.