Rupak
@rupak-s.bsky.social
4th year PhD student in UMD CS advised by Philip Resnik. I have also been a research intern at MSR (2024) and Adobe Research (2022).
Pinned
Rupak
@rupak-s.bsky.social
· May 1
Are you tired of using traditional stance detection to measure the polarity of text? Our #NAACL25 paper proposes an approach that uses pairwise comparisons to order texts on a continuous scale, capturing both implicit and explicit evidence in language.
📍Today in Hall 3 from 4-5:30pm
Come say hi!
📍Today in Hall 3 from 4-5:30pm
Come say hi!
Reposted by Rupak
LLMs didn’t move language modeling research from linguists to AI people, they just moved it from computer scientists who thought language was interesting to computer scientists who thought language was boring
December 12, 2025 at 7:38 PM
LLMs didn’t move language modeling research from linguists to AI people, they just moved it from computer scientists who thought language was interesting to computer scientists who thought language was boring
Reposted by Rupak
AI is already at work in American newsrooms.
We examine 186k articles published this summer and find that ~9% are either fully or partially AI-generated, usually without readers having any idea.
Here's what we learned about how AI is influencing local and national journalism:
We examine 186k articles published this summer and find that ~9% are either fully or partially AI-generated, usually without readers having any idea.
Here's what we learned about how AI is influencing local and national journalism:
October 22, 2025 at 3:24 PM
AI is already at work in American newsrooms.
We examine 186k articles published this summer and find that ~9% are either fully or partially AI-generated, usually without readers having any idea.
Here's what we learned about how AI is influencing local and national journalism:
We examine 186k articles published this summer and find that ~9% are either fully or partially AI-generated, usually without readers having any idea.
Here's what we learned about how AI is influencing local and national journalism:
Reposted by Rupak
Do you have strong programming skills but need research experience doing meaningful & exciting CSS projects before heading off to a top graduate school for computational social science PhD? Apply now to predoc with me,
@dggoldst.bsky.social @jakehofman.bsky.social www.microsoft.com/en-us/resear...
@dggoldst.bsky.social @jakehofman.bsky.social www.microsoft.com/en-us/resear...
Predoctoral Research Assistant (Contract) – Computational Social Science - Microsoft Research
Are you a recent college graduate wishing to gain research experience prior to pursuing a Ph.D. in fields related to computational social science (CSS)? Do you have a deep love of “playing with data”—...
www.microsoft.com
July 10, 2025 at 3:48 PM
Do you have strong programming skills but need research experience doing meaningful & exciting CSS projects before heading off to a top graduate school for computational social science PhD? Apply now to predoc with me,
@dggoldst.bsky.social @jakehofman.bsky.social www.microsoft.com/en-us/resear...
@dggoldst.bsky.social @jakehofman.bsky.social www.microsoft.com/en-us/resear...
Reposted by Rupak
Evaluating topic models (and document clustering methods) is hard. In fact, since our paper critiquing standard evaluation practices four years ago, there hasn't been a good replacement metric
That ends today (we hope)! Our new ACL paper introduces an LLM-based evaluation protocol 🧵
That ends today (we hope)! Our new ACL paper introduces an LLM-based evaluation protocol 🧵
July 8, 2025 at 12:40 PM
Evaluating topic models (and document clustering methods) is hard. In fact, since our paper critiquing standard evaluation practices four years ago, there hasn't been a good replacement metric
That ends today (we hope)! Our new ACL paper introduces an LLM-based evaluation protocol 🧵
That ends today (we hope)! Our new ACL paper introduces an LLM-based evaluation protocol 🧵
Reposted by Rupak
Honored by the feature on my research, grant, and GPU cluster by the Williams magazine. today.williams.edu/magazine/a-c...
A Co-op for Computing
Faculty are diving into the exciting, data-crunching, AI world of GPMoo.
today.williams.edu
May 28, 2025 at 1:41 AM
Honored by the feature on my research, grant, and GPU cluster by the Williams magazine. today.williams.edu/magazine/a-c...
Are you tired of using traditional stance detection to measure the polarity of text? Our #NAACL25 paper proposes an approach that uses pairwise comparisons to order texts on a continuous scale, capturing both implicit and explicit evidence in language.
📍Today in Hall 3 from 4-5:30pm
Come say hi!
📍Today in Hall 3 from 4-5:30pm
Come say hi!
May 1, 2025 at 3:08 PM
Are you tired of using traditional stance detection to measure the polarity of text? Our #NAACL25 paper proposes an approach that uses pairwise comparisons to order texts on a continuous scale, capturing both implicit and explicit evidence in language.
📍Today in Hall 3 from 4-5:30pm
Come say hi!
📍Today in Hall 3 from 4-5:30pm
Come say hi!
Check out Neha’s Outstanding Paper Award 🏆 winning research on atomic hypothesis decomposition in Session C at 2 pm today!!
#NAACL2025
#NAACL2025
I'll be presenting this work with @rachelrudinger at #NAACL2025 tomorrow (Wednesday 4/30) in Albuquerque during Session C (Oral/Poster 2) at 2pm! 🔬
Decomposing hypotheses in traditional NLI and defeasible NLI helps us measure various forms of consistency of LLMs. Come join us!
Decomposing hypotheses in traditional NLI and defeasible NLI helps us measure various forms of consistency of LLMs. Come join us!
April 30, 2025 at 2:11 PM
Check out Neha’s Outstanding Paper Award 🏆 winning research on atomic hypothesis decomposition in Session C at 2 pm today!!
#NAACL2025
#NAACL2025
Reposted by Rupak
I'll be presenting this work with @rachelrudinger at #NAACL2025 tomorrow (Wednesday 4/30) in Albuquerque during Session C (Oral/Poster 2) at 2pm! 🔬
Decomposing hypotheses in traditional NLI and defeasible NLI helps us measure various forms of consistency of LLMs. Come join us!
Decomposing hypotheses in traditional NLI and defeasible NLI helps us measure various forms of consistency of LLMs. Come join us!
April 29, 2025 at 8:40 PM
I'll be presenting this work with @rachelrudinger at #NAACL2025 tomorrow (Wednesday 4/30) in Albuquerque during Session C (Oral/Poster 2) at 2pm! 🔬
Decomposing hypotheses in traditional NLI and defeasible NLI helps us measure various forms of consistency of LLMs. Come join us!
Decomposing hypotheses in traditional NLI and defeasible NLI helps us measure various forms of consistency of LLMs. Come join us!
Reposted by Rupak
🚨 New Paper 🚨
1/ We often assume that well-written text is easier to translate ✏️
But can #LLMs automatically rewrite inputs to improve machine translation? 🌍
Here’s what we found 🧵
1/ We often assume that well-written text is easier to translate ✏️
But can #LLMs automatically rewrite inputs to improve machine translation? 🌍
Here’s what we found 🧵
April 17, 2025 at 1:32 AM
🚨 New Paper 🚨
1/ We often assume that well-written text is easier to translate ✏️
But can #LLMs automatically rewrite inputs to improve machine translation? 🌍
Here’s what we found 🧵
1/ We often assume that well-written text is easier to translate ✏️
But can #LLMs automatically rewrite inputs to improve machine translation? 🌍
Here’s what we found 🧵
I asked Claude 3.7 to count the number of r's in Strawberry ("count the number of r's in strawberry for me") and it wrote a react app that displays a Strawberry, and you click the strawberry to enumerate the number of r's.
Wild. Wondering what kind of alignment policies led to this.
Wild. Wondering what kind of alignment policies led to this.
February 26, 2025 at 1:01 AM
I asked Claude 3.7 to count the number of r's in Strawberry ("count the number of r's in strawberry for me") and it wrote a react app that displays a Strawberry, and you click the strawberry to enumerate the number of r's.
Wild. Wondering what kind of alignment policies led to this.
Wild. Wondering what kind of alignment policies led to this.