Shashank Srivastava

Assistant Prof. at UNC Chapel Hill.
I do research on language and AI.

Previously @MSFTResearch, @mldcmu

[Kerem Zaman @KeremZaman3]

🚨 Is Chain-of-Thought really “not explainability”?

Recent papers claim CoTs are mostly unfaithful because models often fail to verbalize hints that flip their answers.

In our last paper of the year w/ @shsriva, we show this conclusion is misleading. (1/10 🧵)

[Özgür Kara @ozgurkara99]

Hi everyone, I am thrilled to share that our recent study “Optimization-Free Image Immunization Against Diffusion-Based Editing” is now available on ArXiv.

ArXiv: https://t.co/3eE9LOikXv
Project Webpage: https://t.co/X5PgKQnBlg

[Anvesh Rao @nvshrao]

@emnlpmeeting @rrmenon10 @snigdhac25 @shsriva @unccs @uncnlp @UNC (3/3) We also uncover interesting age and gender biases: for the same actions, models tend to judge Female narrators as more innocent ("NTA/Not-the-A**hole") compared to Male narrators.

Code and Data: https://t.co/3KZu71Os6P

[Anvesh Rao @nvshrao]

(1/3) Check out our latest EMNLP 2024 (Findings) work - “SocialGaze: Improving the Integration of Human Social Norms in Large Language Models”; also to be presented at the 6th WNU @emnlpmeeting !

with @rrmenon10 @snigdhac25 @shsriva
at @unccs @uncnlp @UNC

[UNC AI @unc_ai_group]

We are excited to host our next @UNC NLP/ML Colloquium by Dr. Siva Reddy (@sivareddyg) from @Mila_Quebec @McGillU, talking about:

"Paradoxes in Transformer Language Models: Masking, Positional Encodings, and Routing"!

Happening this Wednesday April 10th, 2-3pm ET in FB141.

[Yunyao Li@ACL’26 @yunyao_li]

👋 5th @dash_workshop is returning to @naaclmeeting 2024 at Mexico City in June.

⏰ Submission deadline: March 22, 2024

Look forward to your amazing work!

Co-organized with @lucian_popa_us (@IBMResearch) @eduarddragut Slobodan Vucetic (@TempleUniv) and @shsriva (@UNC).

[UNC AI @unc_ai_group]

🚨🎓 We have several PhD (and postdoc) openings in NLP+CV+ML+AI in beautiful Chapel Hill 👇

Please RT+apply & ping our faculty for any questions (application-fee waivers & no GRE requirement)!

@mohitban47 @gberta227 @snigdhac25 @TianlongChen4 @shsriva @HuaxiuYaoML + others
🧵

[Kerem Zaman @KeremZaman3]

❓ Did you know you can fuse models to reduce unwanted knowledge like shortcuts and biases?

💡 Fused models keep shared knowledge and forget unshared.

🚨Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion

📄https://t.co/hTUv9QRdsr
@LChoshen @shsriva

[Morehead Planetarium and Science Center @moreheadplanet]

Carolina Science Cafe, @moreheadplanet's free science awareness program is right around the corner!

We will be joined by @shsriva, an Assistant Professor of @unccs.

The first session will be on April 4th from 6-8pm

For more info ℹ️ -> https://t.co/K9BEMWoUL9

@uncnlp

[UNC Computer Science @unccs]

Join CS faculty member, @shsriva, alongside faculty from across campus on FRI, FEB 3 at 3PM ET, as the panel explores - "What is ChatGPT? Where did it come from? What does it mean for science, scholarship, and public life?" Event details here: https://t.co/vYyW2IqqzO

[DaSH @dash_workshop]

📢 #CFP for Workshop on Data Science with Human in the Loop at #EMNLP2022

Submit your best work on how to optimize human-computer cooperation and minimize human effort in NLP tasks and applications.

⏰ Submission deadline: Sept. 7, 2022

More details: https://t.co/Q7EYT0SPWR

[Rakesh R Menon @rrmenon10]

Can we learn to classify purely from language explanations?

Check out our #ACL2022 @aclmeeting paper: "CLUES: A Benchmark for Learning Classifiers from Language Explanations"

https://t.co/SwYxH1heNr

Joint work w/ @sayandgp and adv. @shsriva (1/6)

[Sayan Ghosh @sayandgp]

Check out our #ACL2022 @aclmeeting paper: "ePiC: Employing Proverbs in Context as a Benchmark for Abstract Language Understanding"

Paper: https://t.co/K1EF3WOlmX
Website: https://t.co/rYgW0j4ZqZ

Joint work with advisor @shsriva
@uncnlp
(1/3)

[UNC Computer Science @unccs]

Congratulations to assistant professor Colin Raffel (@colinraffel) recipient of a @NSF CAREER Award. The award will seek to enable community-developed and continually-improved machine learning models. https://t.co/smoKqjOwlO

[Shelley Rusincovitch @rusincovitch]

We're delighted to open registration for our 11th Duke Machine Learning School! This 5-day event, with both in-person & virtual attendance options, will introduce the foundational concepts, coding, and case studies at the heart of modern machine learning. https://t.co/7WpglvseA6

[Workshop on Learning with NL Supervision @LNLSWorkshop]

Interested in:
- training image classifiers & robots using language?
- using info from text corpora in other ML applications?
- understanding the role of language in human concept learning?

Join us for the Workshop on Learning with Natural Language Supervision (@aclmeeting '22)!

[Yunyao Li@ACL’26 @yunyao_li]

😀 Very excited to have @dash_workshop back in #EMNLP2022! We've lined up a stellar list of speakers, including @barbara_plank @SaleemaAmershi @amyxzh and more. More to come soon.

Co-organized with @eduarddragut @shsriva @lucian_popa_us and Slobodan Vucetic.

[UNC AI @unc_ai_group]

Check out our @uncnlp group for your PhD applications! We have no GRE requirements + continue our application-fee waivers! Please RT+apply (we have postdoc openings too) & ping us for any questions!🙂

We strongly encourage diversity. Direct FAQ page link: https://t.co/HCCpXY6UUN

[UNC Computer Science @unccs]

Interested in grad school for CS? Come join @unccs, @dukecompsci, and @cscncsu for DECODING GRAD PROGRAMS IN CS (NOV 12) - a virtual event offering first hand POV from faculty and students.
Register here: https://t.co/zSZNRMbYCR

@UNC_GradSchool
@UNCResearch
@Rewriting_Code

[UNC AI @unc_ai_group]

Here is the full program from @UNCNLP+collaborators at #EMNLP2021 this week ➡️ https://t.co/OcoKgHx0Q6

We're also 𝗵𝗶𝗿𝗶𝗻𝗴 𝗣𝗼𝘀𝘁𝗱𝗼𝗰𝘀+𝗣𝗵𝗗 𝘀𝘁𝘂𝗱𝗲𝗻𝘁𝘀! Plz spread the word & ping faculty @mohitban47 @snigdhac25 @colinraffel @shsriva +students for any questions😀