Bhavya Ghai
@Bhavya__Ghai
Followers
102
Following
1K
Media
5
Statuses
64
Applied Scientist @ Amazon, PhD from Stony Brook. Algorithmic Fairness + Human-Centered AI + Data Visualization. Tweets are my own.
New York, New York
Joined May 2020
The HaLLMark Effect: Supporting Provenance and Transparent Use of Large Language Models in Writing with Interactive Visualization. w @mashiat_tasfia @Bhavya__Ghai Cecilia Shelton @fanny_uoft @karikraus @NElmqvist Preprint:
1
2
4
#LongCovid #Covid19 friends, I need urgent help: wife tested positive for covid. It's bad. Doc is refusing to prescribe #Paxlovid citing she's <50yrs. Said LongCovid isn't real. In GA, how might we get Paxlovid? Our doc offices are closed. Please RT + help.
3
3
5
Will LLMs (e.g., chatGPT) replace fiction writers? In our upcoming #DIS2023 paper with @NElmqvist, @Bhavya__Ghai , and @karikraus, we explore how AI and Visualization can extract and represent nuance character traits from a fiction. (1/n)
1
5
22
📢 WE'RE HIRING @mozilla! 📢 Position: fellow in responsible computing FT one-year contract, remote US, $90k/year This is really a special team to work with on so many important issues. Humanities expertise esp welcome. Feel free to share widely! https://t.co/lbyMavHwJQ
9
119
184
The @FAccTConference #FAccT23 Call for Volunteers is now live! This is a great way to support the conference while engaging directly with community members. No prior volunteering experience necessary. Apply to be a volunteer by April 15! https://t.co/NyiZU9MjGM
1
8
15
The AI race is totally out of control. Here’s what Snap’s AI told @aza when he signed up as a 13 year old girl. - How to lie to her parents about a trip with a 31 yo man - How to make losing her virginity on her 13th bday special (candles and music) Our kids are not a test lab.
313
1K
5K
I recently came across data on who we spend our time with over the course of our lives. The insights are simultaneously inspiring and depressing. Here are 6 graphs everyone needs to see:
1K
22K
69K
@trustworthy_ml We found that our human-in-the-loop approach performed significantly better on Trust and Accountability compared to the automated debiasing approach.
0
0
0
@trustworthy_ml Paper: https://t.co/zFLlBldepF Demo video: https://t.co/miDRBvLH2O LIVE Demo: http://130.245.128.219:2800/
0
1
1
Interested in AI Fairness? Check out my latest paper where I present a human-in-the-loop approach to tackle algorithmic bias using causal models. If you are at #ieeevis, come see my talk today at 2PM. #responsibleAI #AI #AIEthics @trustworthy_ml
2
3
8
Paper summary https://t.co/1PERnhyjKn For more, including its code, see
github.com
Studying the Cumulative Effect of Multiple Fairness-Enhancing Interventions on Fairness, Accuracy and Population groups - bhavyaghai/Cascaded-Debiasing
0
0
0
📢 Can we achieve more fairness by using a series of interventions at different stages of the ML pipeline? What are its possible fallouts? To know more, check our #CIKM2022 paper https://t.co/9UpAXYx4yg
#responsibleAI #AIEthics #ai @trustworthy_ml
dl.acm.org
1
4
2
New Fellowship Program @stonybrooku: Inclusion, Diversity, Equity & Access (IDEA) Fellows. A 2 year non-tenure-track lecturer position with a path to tenure track within Stony Brook. There are 5 broad topics, https://t.co/JSpGDjTGs0
1
6
10
Check out our new work w @NElmqvist @Bhavya__Ghai
A book's cast of characters can be true-to-life or embody regressive stereotypes. A new artificial intelligence tool developed by researchers @UofMaryland's Human-Computer Interaction Lab (@hcil_umd), helps writers to spot the difference. Read more: https://t.co/iu48aMm7Z9
0
1
3
(Plz help RT) With new semester coming, we @trustworthy_ml will resume the reading group, and potentially more to benefit the community. Please fill in the form if interested in reading group, peer-review, or virtual research group about trustworthy ML:
docs.google.com
Hi, Thank you for your interest. We plan to resume the reading group at Fall 2022 Please suggest the papers you are interested to discussing with other peers. There are also a couple of other survey...
1
30
88
New Achievement Unlocked - Saw my first patent listed on my google scholar profile! Big thanks to @zywind , @QVeraLiao and Klaus Mueller for their support 🙏 #phdlife
2
0
11
Our #DIS2022 paper w @Bhavya__Ghai and @NElmqvist on supporting creative writers in social bias mitigation is available on ACM DL now: https://t.co/voOef5AfNR. A short thread on it: (1/n)
dl.acm.org
1
3
7
📢Can we enhance algorithmic fairness by applying multiple fairness enhancing interventions at different stages of the ML pipeline? What might be its possible fallouts? To know more, check out our upcoming work @mtlaiethics
#ai #aiethics #responsibleAI
https://t.co/1PERnhxLUP
montrealethics.ai
🔬 Research Summary by Bhavya Ghai, a PhD Candidate at the Computer Science Department, Stony Brook University working on the identification and mitigation of social biases in ML systems.
1
4
7