Ercong Nie
@ercong-nie.bsky.social
PhD student in computational linguistics & NLP at CIS, LMU Munich, junior member at MCML, previously at SJTU.
ercong21.github.io
ercong21.github.io
Reposted by Ercong Nie
🇦🇹I'll be at #ACL2025! Recently I've been thinking about:
✨linguistically + cognitively-motivated evals (as always!)
✨understanding multilingualism + representation learning (new!)
I'll also be presenting a poster for BehaviorBox on Wed @ Poster Session 4 (Hall 4/5, 10-11:30)!
✨linguistically + cognitively-motivated evals (as always!)
✨understanding multilingualism + representation learning (new!)
I'll also be presenting a poster for BehaviorBox on Wed @ Poster Session 4 (Hall 4/5, 10-11:30)!
When it comes to text prediction, where does one LM outperform another? If you've ever worked on LM evals, you know this question is a lot more complex than it seems. In our new #acl2025 paper, we developed a method to find fine-grained differences between LMs:
🧵1/9
🧵1/9
July 25, 2025 at 6:06 PM
🇦🇹I'll be at #ACL2025! Recently I've been thinking about:
✨linguistically + cognitively-motivated evals (as always!)
✨understanding multilingualism + representation learning (new!)
I'll also be presenting a poster for BehaviorBox on Wed @ Poster Session 4 (Hall 4/5, 10-11:30)!
✨linguistically + cognitively-motivated evals (as always!)
✨understanding multilingualism + representation learning (new!)
I'll also be presenting a poster for BehaviorBox on Wed @ Poster Session 4 (Hall 4/5, 10-11:30)!
Excited to be at #ACL2025NLP #acl2025
@aclmeeting in Vienna 🇦🇹 to present our latest work at both the main conference and workshops!
If you're interested in multilingual NLP, human-inspired interpretability of LLMs, or related topics, feel free to stop by and say hi 👋
@aclmeeting in Vienna 🇦🇹 to present our latest work at both the main conference and workshops!
If you're interested in multilingual NLP, human-inspired interpretability of LLMs, or related topics, feel free to stop by and say hi 👋
July 24, 2025 at 8:44 PM
Excited to be at #ACL2025NLP #acl2025
@aclmeeting in Vienna 🇦🇹 to present our latest work at both the main conference and workshops!
If you're interested in multilingual NLP, human-inspired interpretability of LLMs, or related topics, feel free to stop by and say hi 👋
@aclmeeting in Vienna 🇦🇹 to present our latest work at both the main conference and workshops!
If you're interested in multilingual NLP, human-inspired interpretability of LLMs, or related topics, feel free to stop by and say hi 👋
Reposted by Ercong Nie
“Child-Directed Language Does Not Consistently Boost Syntax Learning in Language Models”
I’m happy to share that the preprint of my first PhD project is now online!
🎊 Paper: arxiv.org/abs/2505.23689
I’m happy to share that the preprint of my first PhD project is now online!
🎊 Paper: arxiv.org/abs/2505.23689
Child-Directed Language Does Not Consistently Boost Syntax Learning in Language Models
Seminal work by Huebner et al. (2021) showed that language models (LMs) trained on English Child-Directed Language (CDL) can reach similar syntactic abilities as LMs trained on much larger amounts of ...
arxiv.org
May 30, 2025 at 7:40 AM
“Child-Directed Language Does Not Consistently Boost Syntax Learning in Language Models”
I’m happy to share that the preprint of my first PhD project is now online!
🎊 Paper: arxiv.org/abs/2505.23689
I’m happy to share that the preprint of my first PhD project is now online!
🎊 Paper: arxiv.org/abs/2505.23689
Reposted by Ercong Nie
Bavarian dialect speakers needed! Our MSc student Miriam wants to find out 1. how good/bad LLM-generated "Bavarian" is, and 2. whether dialect speakers agree with each other on this. The survey takes <5 min: survey.ifkw.lmu.de/dialquali25/ Thank you for sharing/participating!
May 30, 2025 at 2:17 PM
Bavarian dialect speakers needed! Our MSc student Miriam wants to find out 1. how good/bad LLM-generated "Bavarian" is, and 2. whether dialect speakers agree with each other on this. The survey takes <5 min: survey.ifkw.lmu.de/dialquali25/ Thank you for sharing/participating!
Reposted by Ercong Nie
📣 Call for Paper Alert: TokShop @ ICML 2025
TokShop explores tokenization across all data modalities. Topics include: subword NLP techniques, multimodal approaches, multilingual challenges, post-training modification, alternative representations, and statistical perspectives.
TokShop explores tokenization across all data modalities. Topics include: subword NLP techniques, multimodal approaches, multilingual challenges, post-training modification, alternative representations, and statistical perspectives.
ICML 2025 Workshop TokShop
Welcome to the OpenReview homepage for ICML 2025 Workshop TokShop
openreview.net
May 14, 2025 at 1:31 PM
📣 Call for Paper Alert: TokShop @ ICML 2025
TokShop explores tokenization across all data modalities. Topics include: subword NLP techniques, multimodal approaches, multilingual challenges, post-training modification, alternative representations, and statistical perspectives.
TokShop explores tokenization across all data modalities. Topics include: subword NLP techniques, multimodal approaches, multilingual challenges, post-training modification, alternative representations, and statistical perspectives.
Reposted by Ercong Nie
Are LM more than their behavior?
Join our @colmweb.org workshop and explore the interplay between what LMs answer and what happens internally ✨
See you in Montréal 🍁
CfP: shorturl.at/sBomu
Page: shorturl.at/FT3fX
Reviewer Nomination: shorturl.at/Jg1BP
#nlproc #interpretability
Join our @colmweb.org workshop and explore the interplay between what LMs answer and what happens internally ✨
See you in Montréal 🍁
CfP: shorturl.at/sBomu
Page: shorturl.at/FT3fX
Reviewer Nomination: shorturl.at/Jg1BP
#nlproc #interpretability
May 30, 2025 at 6:58 AM
Are LM more than their behavior?
Join our @colmweb.org workshop and explore the interplay between what LMs answer and what happens internally ✨
See you in Montréal 🍁
CfP: shorturl.at/sBomu
Page: shorturl.at/FT3fX
Reviewer Nomination: shorturl.at/Jg1BP
#nlproc #interpretability
Join our @colmweb.org workshop and explore the interplay between what LMs answer and what happens internally ✨
See you in Montréal 🍁
CfP: shorturl.at/sBomu
Page: shorturl.at/FT3fX
Reviewer Nomination: shorturl.at/Jg1BP
#nlproc #interpretability
Three papers accepted to ACL 2025🥰
On cross-lingual knowledge editing, probing, and multilingual interpretability🔍
Sincere thanks to all the amazing coauthors and supervisors! ❤️
Looking forward to meeting old friends and knowing new people soon in Vienna! 🇦🇹
On cross-lingual knowledge editing, probing, and multilingual interpretability🔍
Sincere thanks to all the amazing coauthors and supervisors! ❤️
Looking forward to meeting old friends and knowing new people soon in Vienna! 🇦🇹
May 17, 2025 at 11:25 PM
Three papers accepted to ACL 2025🥰
On cross-lingual knowledge editing, probing, and multilingual interpretability🔍
Sincere thanks to all the amazing coauthors and supervisors! ❤️
Looking forward to meeting old friends and knowing new people soon in Vienna! 🇦🇹
On cross-lingual knowledge editing, probing, and multilingual interpretability🔍
Sincere thanks to all the amazing coauthors and supervisors! ❤️
Looking forward to meeting old friends and knowing new people soon in Vienna! 🇦🇹
Reposted by Ercong Nie
🛎️ Excited to announce the 1st Workshop on Bridging NLP and Public Opinion Research at COLM 2025, Oct 10th in Montreal 🇨🇦
As LLMs reshape public discourse and research, collaboration between NLP and Public Opinion Research (POR) is more vital than ever #NLPOR Submit by June 23📄
🔗 tinyurl.com/nlpor25
As LLMs reshape public discourse and research, collaboration between NLP and Public Opinion Research (POR) is more vital than ever #NLPOR Submit by June 23📄
🔗 tinyurl.com/nlpor25
May 16, 2025 at 1:24 PM
🛎️ Excited to announce the 1st Workshop on Bridging NLP and Public Opinion Research at COLM 2025, Oct 10th in Montreal 🇨🇦
As LLMs reshape public discourse and research, collaboration between NLP and Public Opinion Research (POR) is more vital than ever #NLPOR Submit by June 23📄
🔗 tinyurl.com/nlpor25
As LLMs reshape public discourse and research, collaboration between NLP and Public Opinion Research (POR) is more vital than ever #NLPOR Submit by June 23📄
🔗 tinyurl.com/nlpor25
COMPS is a fantastic work for evaluating concept understanding (EACL 2023 best paper). Now, we aim to extend it to 17 languages for exploring multilingual concept understanding (with minimal pair probing). Check our latest findings.
Co-worked with @linyanghe.bsky.social
Co-worked with @linyanghe.bsky.social
COMPS (aclanthology.org/2023.eacl-ma...) now also available in 17 additional languages! A valiant effort by He and Nie et al. 🙏
Check it out here: arxiv.org/abs/2502.19737
Check it out here: arxiv.org/abs/2502.19737
April 3, 2025 at 12:25 AM
COMPS is a fantastic work for evaluating concept understanding (EACL 2023 best paper). Now, we aim to extend it to 17 languages for exploring multilingual concept understanding (with minimal pair probing). Check our latest findings.
Co-worked with @linyanghe.bsky.social
Co-worked with @linyanghe.bsky.social