Excited to share 2 papers at #NAACL2025 main!
📄✍️ MoDS: Multi-Doc Summarization for Debatable Queries (Adobe intern work, coming soon!)
🤔❓Reverse QA: LLMs struggle with the simple task of giving questions for answers
Grateful for all my collaborators 😁
📄✍️ MoDS: Multi-Doc Summarization for Debatable Queries (Adobe intern work, coming soon!)
🤔❓Reverse QA: LLMs struggle with the simple task of giving questions for answers
Grateful for all my collaborators 😁
January 31, 2025 at 2:32 PM
Excited to share 2 papers at #NAACL2025 main!
📄✍️ MoDS: Multi-Doc Summarization for Debatable Queries (Adobe intern work, coming soon!)
🤔❓Reverse QA: LLMs struggle with the simple task of giving questions for answers
Grateful for all my collaborators 😁
📄✍️ MoDS: Multi-Doc Summarization for Debatable Queries (Adobe intern work, coming soon!)
🤔❓Reverse QA: LLMs struggle with the simple task of giving questions for answers
Grateful for all my collaborators 😁
📎paper: openreview.net/forum?id=eFG...
📎#1 daily paper at HF: huggingface.co/papers/2410....
📎code: github.com/tianyi-lab/M...
Led by Ziyue Li at UMD CS, who is also the 1st author of MosT #ICLR2025 and SMoA #NAACL2025🔍Ziyue is looking for Intern
More details👇
📎#1 daily paper at HF: huggingface.co/papers/2410....
📎code: github.com/tianyi-lab/M...
Led by Ziyue Li at UMD CS, who is also the 1st author of MosT #ICLR2025 and SMoA #NAACL2025🔍Ziyue is looking for Intern
More details👇
Your Mixture-of-Experts LLM Is Secretly an Embedding Model for Free
While large language models (LLMs) excel on generation tasks, their decoder-only architecture often limits their potential as embedding models if no further representation finetuning is applied....
openreview.net
February 13, 2025 at 3:26 PM
📎paper: openreview.net/forum?id=eFG...
📎#1 daily paper at HF: huggingface.co/papers/2410....
📎code: github.com/tianyi-lab/M...
Led by Ziyue Li at UMD CS, who is also the 1st author of MosT #ICLR2025 and SMoA #NAACL2025🔍Ziyue is looking for Intern
More details👇
📎#1 daily paper at HF: huggingface.co/papers/2410....
📎code: github.com/tianyi-lab/M...
Led by Ziyue Li at UMD CS, who is also the 1st author of MosT #ICLR2025 and SMoA #NAACL2025🔍Ziyue is looking for Intern
More details👇
The @milanlp.bsky.social lab is presenting 6 papers at #NAACL2025!
May 2, 2025 at 2:41 PM
The @milanlp.bsky.social lab is presenting 6 papers at #NAACL2025!
Love this! I mostly only use curated feeds (based on lists of users) except for my paper feeds and conference feeds. Maybe you could look for people posting with conference hashtags like #NAACL2025, #NEURIPS2025?
May 3, 2025 at 3:21 PM
Love this! I mostly only use curated feeds (based on lists of users) except for my paper feeds and conference feeds. Maybe you could look for people posting with conference hashtags like #NAACL2025, #NEURIPS2025?
An even better #NAACL2025 feed!
If you're at NAACL this week (or just want to keep track), I have a feed for you: bsky.app/profile/did:...
Currently pulling everyone that mentions NAACL, posts a link from the ACL Anthology, or has NAACL in their username. Happy conferencing!
Currently pulling everyone that mentions NAACL, posts a link from the ACL Anthology, or has NAACL in their username. Happy conferencing!
April 30, 2025 at 5:27 PM
An even better #NAACL2025 feed!
I made a #NAACL2025 feed that will match that hashtag and the "NAACL" string (not case sensitive). You can pin the feed so that it's easily accessible from your home page. Enjoy!
April 30, 2025 at 7:18 AM
I made a #NAACL2025 feed that will match that hashtag and the "NAACL" string (not case sensitive). You can pin the feed so that it's easily accessible from your home page. Enjoy!
Sadly I'm not at #NAACL2025 but @lasha.bsky.social is there to present this paper, which I helped with a bit and really like! Find her if you'd like to chat about memorization!
Want to know what training data has been memorized by models like GPT-4?
We propose information-guided probes, a method to uncover memorization evidence in *completely black-box* models,
without requiring access to
🙅♀️ Model weights
🙅♀️ Training data
🙅♀️ Token probabilities 🧵 (1/5)
We propose information-guided probes, a method to uncover memorization evidence in *completely black-box* models,
without requiring access to
🙅♀️ Model weights
🙅♀️ Training data
🙅♀️ Token probabilities 🧵 (1/5)
Information-Guided Identification of Training Data Imprint in (Proprietary) Large Language Models
High-quality training data has proven crucial for developing performant large language models (LLMs). However, commercial LLM providers disclose few, if any, details about the data used for training. ...
arxiv.org
April 30, 2025 at 6:28 AM
Sadly I'm not at #NAACL2025 but @lasha.bsky.social is there to present this paper, which I helped with a bit and really like! Find her if you'd like to chat about memorization!
🚨 New Paper Accepted at #NAACL2025 🚨
"Conformalized Answer Set Prediction for Knowledge Graph Embedding"
@yuqichengzhu.bsky.social, Nico Potyka, Jiarong Pan, @boxiong.bsky.social, Yunjie He, Evgeny Kharlamov, @ststaab.bsky.social
✨Check out our paper: arxiv.org/pdf/2408.082...
"Conformalized Answer Set Prediction for Knowledge Graph Embedding"
@yuqichengzhu.bsky.social, Nico Potyka, Jiarong Pan, @boxiong.bsky.social, Yunjie He, Evgeny Kharlamov, @ststaab.bsky.social
✨Check out our paper: arxiv.org/pdf/2408.082...
January 28, 2025 at 12:21 PM
🚨 New Paper Accepted at #NAACL2025 🚨
"Conformalized Answer Set Prediction for Knowledge Graph Embedding"
@yuqichengzhu.bsky.social, Nico Potyka, Jiarong Pan, @boxiong.bsky.social, Yunjie He, Evgeny Kharlamov, @ststaab.bsky.social
✨Check out our paper: arxiv.org/pdf/2408.082...
"Conformalized Answer Set Prediction for Knowledge Graph Embedding"
@yuqichengzhu.bsky.social, Nico Potyka, Jiarong Pan, @boxiong.bsky.social, Yunjie He, Evgeny Kharlamov, @ststaab.bsky.social
✨Check out our paper: arxiv.org/pdf/2408.082...
outstanding paper award for our AI in Education work!
🐟 dataset of natural images of student solutions to K-12 math problems from online teaching platform
🐠 annotations (dense captions, VQA pairs) by teachers to eval VLMs
find our leads @samibaral.bsky.social @lucy3.bsky.social at #NAACL2025 🤩
🐟 dataset of natural images of student solutions to K-12 math problems from online teaching platform
🐠 annotations (dense captions, VQA pairs) by teachers to eval VLMs
find our leads @samibaral.bsky.social @lucy3.bsky.social at #NAACL2025 🤩
April 28, 2025 at 5:45 PM
outstanding paper award for our AI in Education work!
🐟 dataset of natural images of student solutions to K-12 math problems from online teaching platform
🐠 annotations (dense captions, VQA pairs) by teachers to eval VLMs
find our leads @samibaral.bsky.social @lucy3.bsky.social at #NAACL2025 🤩
🐟 dataset of natural images of student solutions to K-12 math problems from online teaching platform
🐠 annotations (dense captions, VQA pairs) by teachers to eval VLMs
find our leads @samibaral.bsky.social @lucy3.bsky.social at #NAACL2025 🤩
Heading to #NAACL2025 We are hiring full-time scientists on LLM post training, long-context reasoning, agents, and reinforcement finetuning. Please reach out if you are interested in chatting at the conference!
April 26, 2025 at 7:58 PM
Heading to #NAACL2025 We are hiring full-time scientists on LLM post training, long-context reasoning, agents, and reinforcement finetuning. Please reach out if you are interested in chatting at the conference!
Had so many fruitful discussions and made many friends this #NAACL2025 🌵🏜️Thanks for everyone who came to my poster or listened to me talking about my audacious thoughts! 😜
(I should have printed more stickers as they were more popular than I anticipated😅)
(I should have printed more stickers as they were more popular than I anticipated😅)
May 6, 2025 at 11:25 PM
Had so many fruitful discussions and made many friends this #NAACL2025 🌵🏜️Thanks for everyone who came to my poster or listened to me talking about my audacious thoughts! 😜
(I should have printed more stickers as they were more popular than I anticipated😅)
(I should have printed more stickers as they were more popular than I anticipated😅)
Imagine getting to talk about memes all day with outstanding researchers like @peterebertc.bsky.social, @preslavnakov.bsky.social, and @igurevych.bsky.social, and then write a paper about it! Come see me at #NAACL2025 if you want to chat memes!
𝗡𝗲𝘄 𝘄𝗼𝗿𝗸 𝗼𝗻 𝘁𝗲𝗺𝗽𝗹𝗮𝘁𝗶𝗰 𝗺𝗲𝗺𝗲𝘀!
We built a knowledge base of 5,200+ meme templates & 54,000+ examples to study their encoded meaning.
Our #NAACL2025 paper shows how we can resplit datasets with templates for better generalization!
📄: arxiv.org/abs/2311.06649 (1/🧵)
#NLProc
We built a knowledge base of 5,200+ meme templates & 54,000+ examples to study their encoded meaning.
Our #NAACL2025 paper shows how we can resplit datasets with templates for better generalization!
📄: arxiv.org/abs/2311.06649 (1/🧵)
#NLProc
April 30, 2025 at 4:34 PM
Imagine getting to talk about memes all day with outstanding researchers like @peterebertc.bsky.social, @preslavnakov.bsky.social, and @igurevych.bsky.social, and then write a paper about it! Come see me at #NAACL2025 if you want to chat memes!
If you are at #NAACL2025 check out our oral: 🔥
"Speculative Diffusion Decoding: Accelerating Language generation through diffusion"
We use discrete diffusion as a drafting model to speed up #LLM inference---up to 7.2x faster over standard generation 🚀
tiny.cc/xt0i001
"Speculative Diffusion Decoding: Accelerating Language generation through diffusion"
We use discrete diffusion as a drafting model to speed up #LLM inference---up to 7.2x faster over standard generation 🚀
tiny.cc/xt0i001
April 29, 2025 at 11:43 AM
If you are at #NAACL2025 check out our oral: 🔥
"Speculative Diffusion Decoding: Accelerating Language generation through diffusion"
We use discrete diffusion as a drafting model to speed up #LLM inference---up to 7.2x faster over standard generation 🚀
tiny.cc/xt0i001
"Speculative Diffusion Decoding: Accelerating Language generation through diffusion"
We use discrete diffusion as a drafting model to speed up #LLM inference---up to 7.2x faster over standard generation 🚀
tiny.cc/xt0i001
Continuing our work on LLMs for content moderation, our #NAACL2025 shows that SLMs can outperform LLMs with higher accuracy, better recall, and easier fine-tuning for community norms—making them a scalable, convenient, and cost-effective choice. /w @agam-goyal.bsky.social @ceshwar.bsky.social
🚨 New #NAACL2025 paper alert: “SLM-Mod: Small Language Models Surpass LLMs at Content Moderation”
We show that fine-tuned small language models outperform LLMs like GPT-4o for content moderation tasks, with higher accuracy and recall!
🔗 arXiv: arxiv.org/pdf/2410.13155
🧵[1/7]
We show that fine-tuned small language models outperform LLMs like GPT-4o for content moderation tasks, with higher accuracy and recall!
🔗 arXiv: arxiv.org/pdf/2410.13155
🧵[1/7]
arxiv.org
April 26, 2025 at 6:06 PM
Continuing our work on LLMs for content moderation, our #NAACL2025 shows that SLMs can outperform LLMs with higher accuracy, better recall, and easier fine-tuning for community norms—making them a scalable, convenient, and cost-effective choice. /w @agam-goyal.bsky.social @ceshwar.bsky.social
📣 Join us tomorrow May 3rd for the 10th Workshop on Noisy and User-generated Text #W-NUT at #NAACL2025 (📍 Room Navajo/Nambe)!
The workshop features 16 paper presentations and 2 exciting keynote talks by @verenablaschke.bsky.social and Su Lin Blodgett (titles+abstracts below)! #NLProc #NAACL
👇
The workshop features 16 paper presentations and 2 exciting keynote talks by @verenablaschke.bsky.social and Su Lin Blodgett (titles+abstracts below)! #NLProc #NAACL
👇
May 2, 2025 at 9:39 PM
📣 Join us tomorrow May 3rd for the 10th Workshop on Noisy and User-generated Text #W-NUT at #NAACL2025 (📍 Room Navajo/Nambe)!
The workshop features 16 paper presentations and 2 exciting keynote talks by @verenablaschke.bsky.social and Su Lin Blodgett (titles+abstracts below)! #NLProc #NAACL
👇
The workshop features 16 paper presentations and 2 exciting keynote talks by @verenablaschke.bsky.social and Su Lin Blodgett (titles+abstracts below)! #NLProc #NAACL
👇
I'll be presenting our work today 🕓 Apr 30th, 16:15 (UTC-6 time) at #NAACL2025 during the R&E.2 oral session (Ballroom A)! Come say hi 😊
📝 aclanthology.org/2025.naacl-l...
#NAACL #NLProc #NLP
📝 aclanthology.org/2025.naacl-l...
#NAACL #NLProc #NLP
Happy to share that “Fine-grained Fallacy Detection with Human Label Variation” with @agnesedaff.bsky.social and @satonelli.bsky.social was accepted to #NAACL2025 main conference 🎉
📝 arxiv.org/abs/2502.13853
#NLProc #NLP #NAACL
1/🧵
📝 arxiv.org/abs/2502.13853
#NLProc #NLP #NAACL
1/🧵
April 30, 2025 at 5:32 PM
I'll be presenting our work today 🕓 Apr 30th, 16:15 (UTC-6 time) at #NAACL2025 during the R&E.2 oral session (Ballroom A)! Come say hi 😊
📝 aclanthology.org/2025.naacl-l...
#NAACL #NLProc #NLP
📝 aclanthology.org/2025.naacl-l...
#NAACL #NLProc #NLP
Happy to share that “Fine-grained Fallacy Detection with Human Label Variation” with @agnesedaff.bsky.social and @satonelli.bsky.social was accepted to #NAACL2025 main conference 🎉
📝 arxiv.org/abs/2502.13853
#NLProc #NLP #NAACL
1/🧵
📝 arxiv.org/abs/2502.13853
#NLProc #NLP #NAACL
1/🧵
February 25, 2025 at 1:40 PM
Happy to share that “Fine-grained Fallacy Detection with Human Label Variation” with @agnesedaff.bsky.social and @satonelli.bsky.social was accepted to #NAACL2025 main conference 🎉
📝 arxiv.org/abs/2502.13853
#NLProc #NLP #NAACL
1/🧵
📝 arxiv.org/abs/2502.13853
#NLProc #NLP #NAACL
1/🧵
MMLU-Redux just touched down at #NAACL2025! 🎉
Wish I could be there for our "Are We Done with MMLU?" poster today (9:00-10:30am in Hall 3, Poster Session 7), but visa drama said nope 😅
If anyone's swinging by, give our research some love! Hit me up if you check it out! 👋
Wish I could be there for our "Are We Done with MMLU?" poster today (9:00-10:30am in Hall 3, Poster Session 7), but visa drama said nope 😅
If anyone's swinging by, give our research some love! Hit me up if you check it out! 👋
May 2, 2025 at 1:00 PM
MMLU-Redux just touched down at #NAACL2025! 🎉
Wish I could be there for our "Are We Done with MMLU?" poster today (9:00-10:30am in Hall 3, Poster Session 7), but visa drama said nope 😅
If anyone's swinging by, give our research some love! Hit me up if you check it out! 👋
Wish I could be there for our "Are We Done with MMLU?" poster today (9:00-10:30am in Hall 3, Poster Session 7), but visa drama said nope 😅
If anyone's swinging by, give our research some love! Hit me up if you check it out! 👋
📣 Second Call for Papers! 🎉
We’re extending our CFP to February 6, 2025 ⏳—more time to submit your work on culture, society & NLP!
📍 C3NLP 2025 @ NAACL | Albuquerque, NM 🌎
📅 New Deadline: Feb 6, 2025
🔗 Workshop details: c3nlp.github.io
Submit now & join us! 📝✨
#NLP #C3NLP #CulturalNLP #NAACL2025
We’re extending our CFP to February 6, 2025 ⏳—more time to submit your work on culture, society & NLP!
📍 C3NLP 2025 @ NAACL | Albuquerque, NM 🌎
📅 New Deadline: Feb 6, 2025
🔗 Workshop details: c3nlp.github.io
Submit now & join us! 📝✨
#NLP #C3NLP #CulturalNLP #NAACL2025
C3NLP @ NAACL 2025
c3nlp.github.io
January 30, 2025 at 1:48 PM
📣 Second Call for Papers! 🎉
We’re extending our CFP to February 6, 2025 ⏳—more time to submit your work on culture, society & NLP!
📍 C3NLP 2025 @ NAACL | Albuquerque, NM 🌎
📅 New Deadline: Feb 6, 2025
🔗 Workshop details: c3nlp.github.io
Submit now & join us! 📝✨
#NLP #C3NLP #CulturalNLP #NAACL2025
We’re extending our CFP to February 6, 2025 ⏳—more time to submit your work on culture, society & NLP!
📍 C3NLP 2025 @ NAACL | Albuquerque, NM 🌎
📅 New Deadline: Feb 6, 2025
🔗 Workshop details: c3nlp.github.io
Submit now & join us! 📝✨
#NLP #C3NLP #CulturalNLP #NAACL2025
If you are at #NAACL2025, checkout Tia's amazing meta-eval work to make sure that you are using your metrics right!!
(Even if you are not at NAACL, do check it out XD)
(Even if you are not at NAACL, do check it out XD)
Ever trusted a metric that works great on average, only for it to fail in your specific use case?
In our #NAACL2025 paper (w/ @841io.bsky.social), we show why global evaluations are not enough and why context matters more than you think.
📄 aclanthology.org/2025.finding...
#NLP #Evaluation
(🧵1/9)
In our #NAACL2025 paper (w/ @841io.bsky.social), we show why global evaluations are not enough and why context matters more than you think.
📄 aclanthology.org/2025.finding...
#NLP #Evaluation
(🧵1/9)
April 29, 2025 at 5:31 PM
If you are at #NAACL2025, checkout Tia's amazing meta-eval work to make sure that you are using your metrics right!!
(Even if you are not at NAACL, do check it out XD)
(Even if you are not at NAACL, do check it out XD)
It is "official" this year -- submit to the Queer in AI workshop at #NAACL2025 🫶
1/7 🌈 BIG NEWS ALERT! The hottest Queer in AI workshop is back - and this time we're official! We're thrilled to announce we'll be at #NAACL2025 as an official workshop, meaning your work can now be published in the ACL anthology! 🎉
December 9, 2024 at 8:12 PM
It is "official" this year -- submit to the Queer in AI workshop at #NAACL2025 🫶
Our work on hybrid (human+AI)-generated misinformation is accepted to #COLM2026
preprint: arxiv.org/abs/2604.09514
The work builds on our #NAACL2025 paper detailing the strategies used by human creators of fake news to enhance AI-generated content.
aclanthology.org/2025.naacl-l...
preprint: arxiv.org/abs/2604.09514
The work builds on our #NAACL2025 paper detailing the strategies used by human creators of fake news to enhance AI-generated content.
aclanthology.org/2025.naacl-l...
Many Ways to Be Fake: Benchmarking Fake News Detection Under Strategy-Driven AI Generation
Recent advances in large language models (LLMs) have enabled the large-scale generation of highly fluent and deceptive news-like content. While prior work has often treated fake news detection as a bi...
arxiv.org
July 9, 2026 at 2:49 PM
Our work on hybrid (human+AI)-generated misinformation is accepted to #COLM2026
preprint: arxiv.org/abs/2604.09514
The work builds on our #NAACL2025 paper detailing the strategies used by human creators of fake news to enhance AI-generated content.
aclanthology.org/2025.naacl-l...
preprint: arxiv.org/abs/2604.09514
The work builds on our #NAACL2025 paper detailing the strategies used by human creators of fake news to enhance AI-generated content.
aclanthology.org/2025.naacl-l...
Super excited to share that our paper "A Logical Fallacy-Informed Framework for Argument Generation" has received the Outstanding Paper Award 🎉🎉 at NAACL 2025!
Paper: aclanthology.org/2025.naacl-l...
Code: github.com/lucamouchel/...
#NAACL2025
Paper: aclanthology.org/2025.naacl-l...
Code: github.com/lucamouchel/...
#NAACL2025
May 1, 2025 at 1:41 PM
Super excited to share that our paper "A Logical Fallacy-Informed Framework for Argument Generation" has received the Outstanding Paper Award 🎉🎉 at NAACL 2025!
Paper: aclanthology.org/2025.naacl-l...
Code: github.com/lucamouchel/...
#NAACL2025
Paper: aclanthology.org/2025.naacl-l...
Code: github.com/lucamouchel/...
#NAACL2025
Excited to have two papers at #NAACL2025!
The first reveals how human over-reliance can be exacerbated by LLM friendliness. The second presents a novel computational method for concept tracing. Check them out!
arxiv.org/pdf/2407.07950
arxiv.org/pdf/2502.05704
The first reveals how human over-reliance can be exacerbated by LLM friendliness. The second presents a novel computational method for concept tracing. Check them out!
arxiv.org/pdf/2407.07950
arxiv.org/pdf/2502.05704
February 19, 2025 at 9:58 PM
Excited to have two papers at #NAACL2025!
The first reveals how human over-reliance can be exacerbated by LLM friendliness. The second presents a novel computational method for concept tracing. Check them out!
arxiv.org/pdf/2407.07950
arxiv.org/pdf/2502.05704
The first reveals how human over-reliance can be exacerbated by LLM friendliness. The second presents a novel computational method for concept tracing. Check them out!
arxiv.org/pdf/2407.07950
arxiv.org/pdf/2502.05704