NielKlug Profile Banner
Ercong Nie Profile
Ercong Nie

@NielKlug

Followers
405
Following
3K
Media
30
Statuses
406

PhD Student in Computational Linguistics & #NLProc @cislmu of @LMU_Muenchen, affiliated member @munichcenterML, Previously @sjtu1896

München, Bayern
Joined March 2018
Don't wanna be here? Send us removal request.
@NielKlug
Ercong Nie
26 days
RT @jixingli: Check out this super cool study on shared meaning representation across languages in brains and languages models 👉🏻.
0
2
0
@NielKlug
Ercong Nie
26 days
RT @aclmeeting: Exciting news! 🎉 We're thrilled to announce an invited talk at ACL 2025 by Professor Luke Zettlemoyer (University of Wash….
2025.aclweb.org
ACL 2025 Conference Overview.
0
9
0
@NielKlug
Ercong Nie
29 days
RT @davlanade: Excited to announce the call for papers for the Multilingual Representation Learning workshop #EMNLP2025 .
0
12
0
@NielKlug
Ercong Nie
1 month
RT @andre_t_martins: Super proud about the EuroLLM/EuroVLM suites! Try it out!.
0
2
0
@NielKlug
Ercong Nie
1 month
RT @megamor2: ✨MLP layers have just become more interpretable than ever ✨.In a new paper:.* We show a simple method for decomposing MLP act….
0
39
0
@NielKlug
Ercong Nie
1 month
RT @WeidiXie: For the soccer fans, don't miss this !!!!⚽️⚽️⚽️⚽️⚽️.
0
1
0
@NielKlug
Ercong Nie
2 months
RT @artetxem: Including English data when adapting LLMs to new languages doesn't affect perplexity, but can have a huge impact in downstrea….
0
11
0
@NielKlug
Ercong Nie
2 months
RT @amir_nlp: New paper: How does pretraining on programming languages + English shape LLMs' concept space?.🔍Do LLMs use English or a progr….
0
13
0
@NielKlug
Ercong Nie
2 months
RT @LucasBandarkar: The unreasonable effectiveness of model merging for cross-lingual transfer !.Our preprint evaluates a number of *modula….
Tweet card summary image
arxiv.org
Large language models (LLMs) still struggle across tasks outside of high-resource languages. In this work, we investigate cross-lingual transfer to lower-resource languages where task-specific...
0
21
0
@NielKlug
Ercong Nie
2 months
RT @Jirui_Qi: [1/]💡New Paper.Large reasoning models (LRMs) are strong in English — but how well do they reason in your language?. Our lates….
0
14
0
@NielKlug
Ercong Nie
2 months
RT @tpimentelms: If you're finishing your camera-ready for ACL (#acl2025nlp) or ICML (#icml2025 ) and want to cite co-first authors more fa….
0
25
0
@NielKlug
Ercong Nie
2 months
RT @amir_nlp: Consider submitting your multilingual NLP work to the MELT workshop @ COLM 2025: Deadline: June 23.
0
5
0
@NielKlug
Ercong Nie
2 months
RT @mingyang2666: 🎉Excited to share our paper on cross-lingual inconsistency is accepted to #ACL2025 🇦🇹!. We dissect why LLMs produce incon….
0
18
0
@NielKlug
Ercong Nie
2 months
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! 🇦🇹
Tweet media one
0
1
8
@NielKlug
Ercong Nie
2 months
RT @gsarti_: BlackboxNLP is back! 💥. Happy to be part of the organizing team for this year, and super excited for our new shared task using….
blackboxnlp.github.io
The Eight Workshop on Analyzing and Interpreting Neural Networks for NLP
0
6
0
@NielKlug
Ercong Nie
2 months
RT @yyzTodd: 🚨 New Blog Drop! .🚀 "Reflection on Knowledge Editing: Charting the Next Steps" is live!.💡 Ever wondered why knowledge editing….
0
16
0
@NielKlug
Ercong Nie
3 months
RT @CanyuChen3: 🔥New #ICLR2025 paper: "𝐂𝐚𝐧 𝐊𝐧𝐨𝐰𝐥𝐞𝐝𝐠𝐞 𝐄𝐝𝐢𝐭𝐢𝐧𝐠 𝐑𝐞𝐚𝐥𝐥𝐲 𝐂𝐨𝐫𝐫𝐞𝐜𝐭 𝐇𝐚𝐥𝐥𝐮𝐜𝐢𝐧𝐚𝐭𝐢𝐨𝐧𝐬?" . Knowledge editing aims to fix false facts in….
0
11
0
@NielKlug
Ercong Nie
3 months
Extending BLiMP multilingually, covering 101 languages, great work!.
@JumeletJ
Jaap Jumelet
4 months
✨New paper ✨ .Introducing 🌍MultiBLiMP 1.0: A Massively Multilingual Benchmark of Minimal Pairs for Subject-Verb Agreement, covering 101 languages! . We present over 125,000 minimal pairs and evaluate 17 LLMs, finding that support is still lacking for many languages. 🧵⬇️
Tweet media one
0
0
2