#nlproc search results

🔥 New paper alert! 🔥 🚀 Excited to announce that the first paper of my PhD, “ProST: Progressive Sub-task Training for Pareto-Optimal Multi-agent Systems Using Small Language Models”, has been accepted at IJCNLP-AACL 2025 (Main) as a long paper! 🧵1/5 #NLProc #AIResearch

bsbijoy2050's tweet image. 🔥  New paper alert! 🔥
🚀 Excited to announce that the first paper of my PhD, “ProST: Progressive Sub-task Training for Pareto-Optimal Multi-agent Systems Using Small Language Models”, has been accepted at IJCNLP-AACL 2025 (Main) as a long paper! 🧵1/5
#NLProc #AIResearch

🎉🎓Congratulations to our PhD student @DennisFucci on a very successful thesis defense! 👏 Many thanks to the evaluation committee members @debora_nozza, @mirco_ravanelli, and Leonardo Badino for their insightful feedback and appreciation of his work! #nlproc

fbk_mt's tweet image. 🎉🎓Congratulations to our PhD student @DennisFucci on a very successful thesis defense! 👏

Many thanks to the evaluation committee members @debora_nozza, @mirco_ravanelli, and Leonardo Badino for their insightful feedback and appreciation of his work!

#nlproc
fbk_mt's tweet image. 🎉🎓Congratulations to our PhD student @DennisFucci on a very successful thesis defense! 👏

Many thanks to the evaluation committee members @debora_nozza, @mirco_ravanelli, and Leonardo Badino for their insightful feedback and appreciation of his work!

#nlproc

The Cardiff #NLProc group and collaborators at #EMNLP2025!

Cardiff_NLP's tweet image. The Cardiff #NLProc group and collaborators at #EMNLP2025!
Cardiff_NLP's tweet image. The Cardiff #NLProc group and collaborators at #EMNLP2025!
Cardiff_NLP's tweet image. The Cardiff #NLProc group and collaborators at #EMNLP2025!
Cardiff_NLP's tweet image. The Cardiff #NLProc group and collaborators at #EMNLP2025!

Photoshop for text. In our #CHI2025 paper “Textoshop”, we explore how interactions inspired by drawing software can help edit text. We consider words as pixels, sentences as regions, and tones as colours. #HCI #NLProc #LLMs #AI Thread 🧵 (1/10)


🚨I'm recruiting a fully funded EPSRC PhD student (start 2026/27) to work with me and @tpilehvar on multilingual misinformation and online harms in #NLProc. (the position is open to UK and international students.) Details and contact information 👇:


🚀 Heading to Suzhou, China for EMNLP 2025 to present our paper “Data‑Efficient Hate Speech Detection via Cross‑Lingual Nearest Neighbor Retrieval with Limited Labeled Data”! Very excited to share our work on applied and cross‑lingual NLP. 🌍📊 #EMNLP2025 #NLProc

FaezeGhorbanpor's tweet image. 🚀 Heading to Suzhou, China for EMNLP 2025 to present our paper “Data‑Efficient Hate Speech Detection via Cross‑Lingual Nearest Neighbor Retrieval with Limited Labeled Data”! 

Very excited to share our work on applied and cross‑lingual NLP. 🌍📊 

#EMNLP2025 #NLProc

Our Book has been "Embodied"! 🥳 "Spatial Language Understanding ..." #NLProc #ACL #EMNLP2025 #AAAI #CVPR link.springer.com/book/10.1007/9…

Kordjamshidi's tweet image. Our Book has been "Embodied"! 🥳 "Spatial Language Understanding ..." #NLProc #ACL #EMNLP2025 #AAAI #CVPR link.springer.com/book/10.1007/9…

Our Cardiff #NLProc group members and collaborators have several papers accepted at #EMNLP2025!🎉 Check out the list of accepted papers, with preprints now available for 👇🧵1/

Cardiff_NLP's tweet image. Our Cardiff #NLProc group members and collaborators have several papers accepted at #EMNLP2025!🎉
Check out the list of accepted papers, with preprints now available for 👇🧵1/

We are honoured to welcome Prof Barbara Plank (@barbara_plank) from @MaiNLPlab, @CisLmu as our keynote speaker at LoResLM 2026. #NLProc #LoResLM @eaclmeeting @hh_hansi @TharinduDR Alistair Plum @perayson @ruslanmitkov @mmmgaber Fiona Anting @DamithPremasiri Lasitha Uyangodage

LoResLM2026's tweet image. We are honoured to welcome Prof Barbara Plank (@barbara_plank) from @MaiNLPlab, @CisLmu as our keynote speaker at LoResLM 2026.

#NLProc #LoResLM @eaclmeeting 

@hh_hansi @TharinduDR Alistair Plum @perayson @ruslanmitkov @mmmgaber Fiona Anting @DamithPremasiri Lasitha Uyangodage

Back after a successful #EMNLP2025 conference in Suzhou, China -- some impressions ⤵️ Our papers: copenlu.com/news/8-papers-… @atanasovapepa @rnav_arora @_kire_kara_ @Shoejoe_ @dustin_wright37 @JingyiSun_ @CopeNLU #NLProc

IAugenstein's tweet image. Back after a successful #EMNLP2025 conference in Suzhou, China -- some impressions ⤵️

Our papers: copenlu.com/news/8-papers-…

@atanasovapepa @rnav_arora @_kire_kara_ @Shoejoe_ @dustin_wright37 @JingyiSun_ @CopeNLU 
#NLProc
IAugenstein's tweet image. Back after a successful #EMNLP2025 conference in Suzhou, China -- some impressions ⤵️

Our papers: copenlu.com/news/8-papers-…

@atanasovapepa @rnav_arora @_kire_kara_ @Shoejoe_ @dustin_wright37 @JingyiSun_ @CopeNLU 
#NLProc
IAugenstein's tweet image. Back after a successful #EMNLP2025 conference in Suzhou, China -- some impressions ⤵️

Our papers: copenlu.com/news/8-papers-…

@atanasovapepa @rnav_arora @_kire_kara_ @Shoejoe_ @dustin_wright37 @JingyiSun_ @CopeNLU 
#NLProc
IAugenstein's tweet image. Back after a successful #EMNLP2025 conference in Suzhou, China -- some impressions ⤵️

Our papers: copenlu.com/news/8-papers-…

@atanasovapepa @rnav_arora @_kire_kara_ @Shoejoe_ @dustin_wright37 @JingyiSun_ @CopeNLU 
#NLProc

All modern LLMs run on top of a tokeniser, an often overlooked “preprocessing detail”. But what if that tokeniser systematically affects model behaviour? We call this tokenisation bias. Let’s talk about it and why it matters👇 @aclmeeting #ACL2025 #NLProc

pietro_lesci's tweet image. All modern LLMs run on top of a tokeniser, an often overlooked “preprocessing detail”. But what if that tokeniser systematically affects model behaviour? We call this tokenisation bias.

Let’s talk about it and why it matters👇 @aclmeeting  #ACL2025 #NLProc

TJUNLP is heading to EMNLP 2025 ✈️ We'll be presenting our latest papers there and looking forward to great discussions! #EMNLP2025 #NLProc

TJUNLP's tweet image. TJUNLP is heading to EMNLP 2025 ✈️
We'll be presenting our latest papers there and looking forward to great discussions!
#EMNLP2025 #NLProc

Testing Grok2 and I am proud that I was ⁦@AyuP_AI⁩’s student and collaborator 😀 #Nlproc

gentaiscool's tweet image. Testing Grok2 and I am proud that I was ⁦@AyuP_AI⁩’s student and collaborator 😀 #Nlproc

Big congratulations to @sewon__min on winning the inaugural ACL Computational Linguistics Dissertation Award at @aclmeeting 2025! #NLProc

stanfordnlp's tweet image. Big congratulations to @sewon__min on winning the inaugural ACL Computational Linguistics Dissertation Award at @aclmeeting 2025!
#NLProc

We're hosting @Diyi_Yang today @mbzuai! I always find her research inspiring and having her here has been a real treat. Her work on human-AI interaction proposes sensible use cases where humans are key part of the solution. #NLProc

thamar_solorio's tweet image. We're hosting @Diyi_Yang today @mbzuai! I always find her research inspiring and having her here has been a real treat. 
Her work on human-AI interaction proposes sensible use cases where humans are key part of the solution.
#NLProc
thamar_solorio's tweet image. We're hosting @Diyi_Yang today @mbzuai! I always find her research inspiring and having her here has been a real treat. 
Her work on human-AI interaction proposes sensible use cases where humans are key part of the solution.
#NLProc

Humbled to take on my 1st ACL Officer position, as Co-Chair of #ACL Ethics Committee. I look forward to promoting Responsible AI in #NLProc community & ensuring ethical research. In my term, I also hope to bridge the narrative w/ AI Safety and various social considerations of AI.

ZhijingJin's tweet image. Humbled to take on my 1st ACL Officer position, as Co-Chair of #ACL Ethics Committee. I look forward to promoting Responsible AI in #NLProc community & ensuring ethical research. In my term, I also hope to bridge the narrative w/ AI Safety and various social considerations of AI.

We (w/ @Diyi_Yang Dirk Hovy and @mbodhisattwa) are excited to present a tutorial on Social Intelligence in the Age of LLMs tomorrow at NAACL 2025. #NAACL25 #NLProc Our talk will highlight the long-standing and emerging challenges of AI interacting w humans, society & the world.

_Hao_Zhu's tweet image. We (w/ @Diyi_Yang Dirk Hovy and @mbodhisattwa) are excited to present a tutorial on Social Intelligence in the Age of LLMs tomorrow at NAACL 2025. #NAACL25  #NLProc Our talk will highlight the long-standing and emerging challenges of AI interacting w humans, society & the world.

New York did not disappoint! Great talks, awesome food, and plenty of ideas to chew on 🍽️🧠 Thanks to my hosts at @NYUDataScience, @Yale, @PrincetonPLI, and @cornell_tech for the fantastic time! Now in Boston - let’s talk #NLProc if you’re around 👋

Itay_itzhak_'s tweet image. New York did not disappoint! Great talks, awesome food, and plenty of ideas to chew on 🍽️🧠
Thanks to my hosts at @NYUDataScience, @Yale,
@PrincetonPLI, and @cornell_tech for the fantastic time!

Now in Boston - let’s talk #NLProc if you’re around 👋
Itay_itzhak_'s tweet image. New York did not disappoint! Great talks, awesome food, and plenty of ideas to chew on 🍽️🧠
Thanks to my hosts at @NYUDataScience, @Yale,
@PrincetonPLI, and @cornell_tech for the fantastic time!

Now in Boston - let’s talk #NLProc if you’re around 👋

I will be giving a keynote on "Rethinking Best Practices for Resource Collection in Cultural NLP" at LMU4C Workshop at NAACL 2025, Room Ruidoso, at 11am. @naaclmeeting #NLProc

gentaiscool's tweet image. I will be giving a keynote on "Rethinking Best Practices for Resource Collection in Cultural NLP" at LMU4C Workshop at NAACL 2025, Room Ruidoso, at 11am.

@naaclmeeting #NLProc

#TBT #NLProc Hessenthaler et al.'s 2022 work delves into AI's link with fairness & energy reduction in English NLP models, challenging bias reduction theories. #AI #NLP #sustainability aclanthology.org/2022.emnlp-mai…


📝 Second Call for Papers for the Workshop on Computational Approaches to Subjectivity, Sentiment, and Social Media Analysis #WASSA2026 at #EACL2026 in Rabat, Morocco 🗓️ Submission deadlines: December 17 (direct) and January 2 (ARR). 🔗 workshop-wassa.github.io #NLProc


We are honoured to welcome Prof Barbara Plank (@barbara_plank) from @MaiNLPlab, @CisLmu as our keynote speaker at LoResLM 2026. #NLProc #LoResLM @eaclmeeting @hh_hansi @TharinduDR Alistair Plum @perayson @ruslanmitkov @mmmgaber Fiona Anting @DamithPremasiri Lasitha Uyangodage

LoResLM2026's tweet image. We are honoured to welcome Prof Barbara Plank (@barbara_plank) from @MaiNLPlab, @CisLmu as our keynote speaker at LoResLM 2026.

#NLProc #LoResLM @eaclmeeting 

@hh_hansi @TharinduDR Alistair Plum @perayson @ruslanmitkov @mmmgaber Fiona Anting @DamithPremasiri Lasitha Uyangodage

Our Book has been "Embodied"! 🥳 "Spatial Language Understanding ..." #NLProc #ACL #EMNLP2025 #AAAI #CVPR link.springer.com/book/10.1007/9…

Kordjamshidi's tweet image. Our Book has been "Embodied"! 🥳 "Spatial Language Understanding ..." #NLProc #ACL #EMNLP2025 #AAAI #CVPR link.springer.com/book/10.1007/9…

I’d like to thank my advisor @b_niranjan for his constant guidance, @aviaviavi__ and @aruna__b for their insightful collaboration and support, and I’m grateful to my co-authors @msaquibhasan and @Pegah_al 📄 Paper: arxiv.org/abs/2509.04508 🧵5/5 #NLProc #MultiStepReasoning


🤖 Does ProST actually reduce failure modes in multi-agent systems? Using MAST (Multi-Agent System Failure Taxonomy) from “Why Do Multi-Agent LLM Systems Fail?”, we found that ProST lowers error rates across all categories vs. standard fine-tuning. 🧵4/5 #AIResearch #NLProc

bsbijoy2050's tweet image. 🤖 Does ProST actually reduce failure modes in multi-agent systems?
Using MAST (Multi-Agent System Failure Taxonomy) from “Why Do Multi-Agent LLM Systems Fail?”, we found that ProST lowers error rates across all categories vs. standard fine-tuning. 🧵4/5
#AIResearch #NLProc

💡 We built a multi-agent framework with: • an Orchestrator (task decomposition) • an Executor (code generation and execution) • a Critic (reflective feedback) Our Pareto analysis shows ProST achieves better effectiveness–efficiency trade-offs. 🧵3/5 #NLProc #MultiAgent

bsbijoy2050's tweet image. 💡 We built a multi-agent framework with:
 • an Orchestrator (task decomposition)
 • an Executor (code generation and execution)
 • a Critic (reflective feedback)

Our Pareto analysis shows ProST achieves better effectiveness–efficiency trade-offs. 🧵3/5
#NLProc #MultiAgent
bsbijoy2050's tweet image. 💡 We built a multi-agent framework with:
 • an Orchestrator (task decomposition)
 • an Executor (code generation and execution)
 • a Critic (reflective feedback)

Our Pareto analysis shows ProST achieves better effectiveness–efficiency trade-offs. 🧵3/5
#NLProc #MultiAgent

Models like Claude, ChatGPT & Gemini excel at multi-step reasoning & coding — but they’re closed-source & costly. Can SLMs learn long-horizon tasks effectively? 🤔 👉 Our paper introduces ProST — Progressive Sub-task Training to teach SLMs multi-step reasoning! 🧵2/5 #NLProc

bsbijoy2050's tweet image. Models like Claude, ChatGPT & Gemini excel at multi-step reasoning & coding — but they’re closed-source & costly.
Can SLMs learn long-horizon tasks effectively? 🤔
👉 Our paper introduces ProST — Progressive Sub-task Training to teach SLMs multi-step reasoning! 🧵2/5
#NLProc

🔥 New paper alert! 🔥 🚀 Excited to announce that the first paper of my PhD, “ProST: Progressive Sub-task Training for Pareto-Optimal Multi-agent Systems Using Small Language Models”, has been accepted at IJCNLP-AACL 2025 (Main) as a long paper! 🧵1/5 #NLProc #AIResearch

bsbijoy2050's tweet image. 🔥  New paper alert! 🔥
🚀 Excited to announce that the first paper of my PhD, “ProST: Progressive Sub-task Training for Pareto-Optimal Multi-agent Systems Using Small Language Models”, has been accepted at IJCNLP-AACL 2025 (Main) as a long paper! 🧵1/5
#NLProc #AIResearch

OpenAI rolls out GPT-5.1 Instant, “warmer” and “more conversational”, and GPT-5.1 Thinking, “easier to understand and faster”, starting with paid ChatGPT users openai.com/index/gpt-5-1/ #OpenAI #nlproc #nlp #voicefirst #chatgpt4 #ChatGPTPlus #GenerativeAI


I need an emergency reviewer for a paper in semantic similarity and embedding model interpretability, please let me know if you can help! #NLProc


Hey :) 🚨🚨 I'm looking for 5 emergency reviewers for ARR submissions: they are all in "Resources and Evaluation"! The reviews need to be submitted within the next 4 days, i.e., Sun 16 Nov AoE 🙃. If you are interested, please DM or email me! #NLProc #NLP #LLMs


Back after a successful #EMNLP2025 conference in Suzhou, China -- some impressions ⤵️ Our papers: copenlu.com/news/8-papers-… @atanasovapepa @rnav_arora @_kire_kara_ @Shoejoe_ @dustin_wright37 @JingyiSun_ @CopeNLU #NLProc

IAugenstein's tweet image. Back after a successful #EMNLP2025 conference in Suzhou, China -- some impressions ⤵️

Our papers: copenlu.com/news/8-papers-…

@atanasovapepa @rnav_arora @_kire_kara_ @Shoejoe_ @dustin_wright37 @JingyiSun_ @CopeNLU 
#NLProc
IAugenstein's tweet image. Back after a successful #EMNLP2025 conference in Suzhou, China -- some impressions ⤵️

Our papers: copenlu.com/news/8-papers-…

@atanasovapepa @rnav_arora @_kire_kara_ @Shoejoe_ @dustin_wright37 @JingyiSun_ @CopeNLU 
#NLProc
IAugenstein's tweet image. Back after a successful #EMNLP2025 conference in Suzhou, China -- some impressions ⤵️

Our papers: copenlu.com/news/8-papers-…

@atanasovapepa @rnav_arora @_kire_kara_ @Shoejoe_ @dustin_wright37 @JingyiSun_ @CopeNLU 
#NLProc
IAugenstein's tweet image. Back after a successful #EMNLP2025 conference in Suzhou, China -- some impressions ⤵️

Our papers: copenlu.com/news/8-papers-…

@atanasovapepa @rnav_arora @_kire_kara_ @Shoejoe_ @dustin_wright37 @JingyiSun_ @CopeNLU 
#NLProc

🔥 New paper alert! 🔥 🚀 Excited to announce that the first paper of my PhD, “ProST: Progressive Sub-task Training for Pareto-Optimal Multi-agent Systems Using Small Language Models”, has been accepted at IJCNLP-AACL 2025 (Main) as a long paper! 🧵1/5 #NLProc #AIResearch

bsbijoy2050's tweet image. 🔥  New paper alert! 🔥
🚀 Excited to announce that the first paper of my PhD, “ProST: Progressive Sub-task Training for Pareto-Optimal Multi-agent Systems Using Small Language Models”, has been accepted at IJCNLP-AACL 2025 (Main) as a long paper! 🧵1/5
#NLProc #AIResearch

🎉🎓Congratulations to our PhD student @DennisFucci on a very successful thesis defense! 👏 Many thanks to the evaluation committee members @debora_nozza, @mirco_ravanelli, and Leonardo Badino for their insightful feedback and appreciation of his work! #nlproc

fbk_mt's tweet image. 🎉🎓Congratulations to our PhD student @DennisFucci on a very successful thesis defense! 👏

Many thanks to the evaluation committee members @debora_nozza, @mirco_ravanelli, and Leonardo Badino for their insightful feedback and appreciation of his work!

#nlproc
fbk_mt's tweet image. 🎉🎓Congratulations to our PhD student @DennisFucci on a very successful thesis defense! 👏

Many thanks to the evaluation committee members @debora_nozza, @mirco_ravanelli, and Leonardo Badino for their insightful feedback and appreciation of his work!

#nlproc

Our Cardiff #NLProc group members and collaborators have several papers accepted at #EMNLP2025!🎉 Check out the list of accepted papers, with preprints now available for 👇🧵1/

Cardiff_NLP's tweet image. Our Cardiff #NLProc group members and collaborators have several papers accepted at #EMNLP2025!🎉
Check out the list of accepted papers, with preprints now available for 👇🧵1/

The Cardiff #NLProc group and collaborators at #EMNLP2025!

Cardiff_NLP's tweet image. The Cardiff #NLProc group and collaborators at #EMNLP2025!
Cardiff_NLP's tweet image. The Cardiff #NLProc group and collaborators at #EMNLP2025!
Cardiff_NLP's tweet image. The Cardiff #NLProc group and collaborators at #EMNLP2025!
Cardiff_NLP's tweet image. The Cardiff #NLProc group and collaborators at #EMNLP2025!

Midwest Speech and Language Days is in full swing at @NotreDame! #NLProc #MSLD2025

davidweichiang's tweet image. Midwest Speech and Language Days is in full swing at @NotreDame! #NLProc #MSLD2025

Commiting my ARR submission to @emnlpmeeting #EMNLP2024 🙃 #NLProc

TuhinChakr's tweet image. Commiting my ARR submission to @emnlpmeeting  #EMNLP2024 🙃 #NLProc

The #NLProc community has thought a lot about human Theory of Mind (ToM), what about Multi-Agents? We are excited to introduce "Agent-to-Agent Theory of Mind", where we test whether #LLMs correctly guess each other's identity after a chat, and also show *adapted behavior*…

ZhijingJin's tweet image. The #NLProc community has thought a lot about human Theory of Mind (ToM), what about Multi-Agents? We are excited to introduce "Agent-to-Agent Theory of Mind", where we test whether #LLMs correctly guess each other's identity after a chat, and also show *adapted behavior*…
ZhijingJin's tweet image. The #NLProc community has thought a lot about human Theory of Mind (ToM), what about Multi-Agents? We are excited to introduce "Agent-to-Agent Theory of Mind", where we test whether #LLMs correctly guess each other's identity after a chat, and also show *adapted behavior*…

Big congratulations to @sewon__min on winning the inaugural ACL Computational Linguistics Dissertation Award at @aclmeeting 2025! #NLProc

stanfordnlp's tweet image. Big congratulations to @sewon__min on winning the inaugural ACL Computational Linguistics Dissertation Award at @aclmeeting 2025!
#NLProc

Im so excited that my work got accepted to FAccT 2025! 🎉 This was the first part of my internship project at Salesforce Research, where we qualitatively explored how LLM-based search fail in delivering holistic, accurate, and verifiable info. #Facct2025 #NLProc @SFResearch

PranavVenkit's tweet image. Im so excited that my work got accepted to FAccT 2025! 🎉

This was the first part of my internship project at Salesforce Research, where we qualitatively explored how LLM-based search fail in delivering holistic, accurate, and verifiable info. #Facct2025 #NLProc @SFResearch

Testing Grok2 and I am proud that I was ⁦@AyuP_AI⁩’s student and collaborator 😀 #Nlproc

gentaiscool's tweet image. Testing Grok2 and I am proud that I was ⁦@AyuP_AI⁩’s student and collaborator 😀 #Nlproc

#NLProc AI Co-Scientists 🤖 can generate ideas, but can they spot mistakes? (not yet! 🚫) In my recent paper, we introduce SPOT, a dataset of STEM manuscripts (math, materials science, chemistry, physics, etc), annotated with real errors. SOTA models like o3, gemini-2.5-pro…

gson_AI's tweet image. #NLProc
AI Co-Scientists 🤖 can generate ideas, but can they spot mistakes? (not yet! 🚫)

In my recent paper, we introduce SPOT, a dataset of STEM manuscripts (math, materials science, chemistry, physics, etc), annotated with real errors.

SOTA models like o3, gemini-2.5-pro…

Finally wrapped up @NeurIPSConf submission, and thrilled to share that 6 papers got accepted to ACL 2025! Big thanks to all my amazing co-authors! 🎉📄 See you in Vienna! 😄 #NLProc #ACL2025NLP

qiushi_sun's tweet image. Finally wrapped up @NeurIPSConf submission, and thrilled to share that 6 papers got accepted to ACL 2025! Big thanks to all my amazing co-authors! 🎉📄

See you in Vienna! 😄 #NLProc #ACL2025NLP

Why do LLMs need far more data than humans? Inspired by the "Less-is-More" hypothesis in human language acquisition, we propose a method for integrating developmental working memory traits into LMs, improving data-efficiency. #NLProc 🔗Read more: arxiv.org/abs/2502.04795

chemical_tree's tweet image. Why do LLMs need far more data than humans? 
Inspired by the "Less-is-More" hypothesis in human language acquisition, we propose a method for integrating developmental working memory traits into LMs, improving data-efficiency. #NLProc  

🔗Read more: arxiv.org/abs/2502.04795

#NLProc Just because GPT-4o is 17 times more expensive than GPT-4o-mini, does that mean it generates synthetic data 17 times better? Introducing the AgoraBench, a benchmark for evaluating data generation capabilities of LMs.

seungonekim's tweet image. #NLProc 
Just because GPT-4o is 17 times more expensive than GPT-4o-mini, does that mean it generates synthetic data 17 times better? 

Introducing the AgoraBench, a benchmark for evaluating data generation capabilities of LMs.

🚨 New paper alert! 🚨 📢 Announcing MuSciClaims, a multimodal claim verification benchmark for heterogeneous, information-rich scientific figures. Such verification is crucial for evaluating scientific hypotheses & ensuring trust and reproducibility in results. 1/6 #NLProc

lal_yash's tweet image. 🚨 New paper alert! 🚨
📢 Announcing MuSciClaims, a multimodal claim verification benchmark for heterogeneous, information-rich scientific figures. Such verification is crucial for evaluating scientific hypotheses & ensuring trust and reproducibility in results. 1/6 #NLProc

We (w/ @Diyi_Yang Dirk Hovy and @mbodhisattwa) are excited to present a tutorial on Social Intelligence in the Age of LLMs tomorrow at NAACL 2025. #NAACL25 #NLProc Our talk will highlight the long-standing and emerging challenges of AI interacting w humans, society & the world.

_Hao_Zhu's tweet image. We (w/ @Diyi_Yang Dirk Hovy and @mbodhisattwa) are excited to present a tutorial on Social Intelligence in the Age of LLMs tomorrow at NAACL 2025. #NAACL25  #NLProc Our talk will highlight the long-standing and emerging challenges of AI interacting w humans, society & the world.

This Thanksgiving, I’m deeply grateful for opportunity to run for NAACL Board Member alongside so many incredible candidates who share a passion for making a difference! I hope to earn your support as we work together to shape the future of our community! #NLProc #Gratitude

VioletNPeng's tweet image. This Thanksgiving, I’m deeply grateful for opportunity to run for NAACL Board Member alongside so many incredible candidates who share a passion for making a difference! 
I hope to earn your support as we work together to shape the future of our community! #NLProc #Gratitude

Humbled to take on my 1st ACL Officer position, as Co-Chair of #ACL Ethics Committee. I look forward to promoting Responsible AI in #NLProc community & ensuring ethical research. In my term, I also hope to bridge the narrative w/ AI Safety and various social considerations of AI.

ZhijingJin's tweet image. Humbled to take on my 1st ACL Officer position, as Co-Chair of #ACL Ethics Committee. I look forward to promoting Responsible AI in #NLProc community & ensuring ethical research. In my term, I also hope to bridge the narrative w/ AI Safety and various social considerations of AI.

Check out the accepted papers from our Cardiff NLP group and collaborators at upcoming #NLProc and #ML conferences (#ACL2025NLP main and findings, #KDD2025)!

Cardiff_NLP's tweet image. Check out the accepted papers from our Cardiff NLP group and collaborators at upcoming #NLProc and #ML conferences (#ACL2025NLP main and findings, #KDD2025)!

Loading...

Something went wrong.


Something went wrong.


United States Trends