Sheffield NLP

933 posts

Sheffield NLP banner
Sheffield NLP

Sheffield NLP

@SheffieldNLP

Established 1993, the University of Sheffield's #NLProc Group is one of the UK's largest natural language processing research centres.

Sheffield, UK Katılım Kasım 2009
150 Takip Edilen3K Takipçiler
Sheffield NLP retweetledi
Xi Wang
Xi Wang@wangxieric·
Today, in our @SheffieldNLP seminar series, we welcome Sean MacAvaney @macavaney from @TerrierTeam at University of Glasgow to give a talk entitled "Re-thinking Re-ranking".
Xi Wang tweet mediaXi Wang tweet media
English
0
1
7
271
Sheffield NLP retweetledi
Constantinos Karouzos
Constantinos Karouzos@ckarouzos·
Thrilled to see such a fantastic breakdown of our latest paper on output diversity collapse in post-training (with @Xingwei__Tan, @nikaletras, @SheffieldNLP)! 🚀 @neural_avb did a phenomenal job summarizing our work. Check it out below! 👇
AVB@neural_avb

I have been studying a lot of post-training paper to prepare for my next video. This morning I am studying a banger from this week: "Where does output diversity collapse in post-training?" One of the more educational papers I have read recently. Basically after post-training LLMs often produce less varied answers than their base versions. This paper runs experiments to figure out where exactly this diversity is lost, the effects of distillation vs instruction-tuning vs RLVR, etc. Their big hypothesis is that the diversity cannot be recovered at inference through sampling techniques or CoT. The collapse irreversibly happens during training.

English
3
2
5
797
Sheffield NLP
Sheffield NLP@SheffieldNLP·
Thanks very much to @sandropezzelle for your brilliant seminar about whether language processing in LLMs reflects human cognitive mechanisms.
Sheffield NLP tweet media
English
2
2
12
908
Sheffield NLP retweetledi
Nikos Aletras
Nikos Aletras@nikaletras·
When we adapt LLMs to other languages using unlabeled target language data, they tend to lose their core instruction-following and reasoning abilities. 🚨 New #ACL2026 paper w/ @_gucciiiii, T. Morishita & @AlineVillav on how to mitigate this catastrophic forgetting 👇
Nikos Aletras tweet media
English
1
3
27
3.2K
Sheffield NLP retweetledi
Nikos Aletras
Nikos Aletras@nikaletras·
Our heart @SheffieldNLP will always be with *ACL, but we've also started getting serious about IR. Great to see our group's efforts in bridging #NLProc & search reflected so clearly in #SIGIR2026. Special shout out to @wangxieric, @drmarkstevenson et al for leading this 👇
Qingyao Ai@QingyaoAi

#SIGIR2026 accepted paper list has been released on sigir2026.org/en-AU/pages/pr… Vibe coded the analysis again based on csrankings.org (again, by no means accurate), found that this year, Renmin University continues to be the top-1 institute, and China and US are still the top-2 countries with most publications.

English
0
3
17
1.5K
Sheffield NLP retweetledi
Nikos Aletras
Nikos Aletras@nikaletras·
LLMs are great at outputting step-by-step reasoning, but is that text actually driving their conclusions, or is it just post-hoc rationalisation? How can we improve the faithfulness of LLM reasoning? My talk at the #EACL2016 FEVER wrkshp aimed to probe a dialogue on this 🧵👇
English
1
1
14
1.3K
Sheffield NLP retweetledi
Joe Stacey
Joe Stacey@_joestacey_·
Excited to share my first postdoc paper with @SheffieldNLP ! 🤩 In this work we argue that supervised uncertainty quantification (UQ) needs better evaluation Want to know more? Here's a little summary 🧵
Joe Stacey tweet media
English
6
9
82
7.4K
Sheffield NLP
Sheffield NLP@SheffieldNLP·
We’re excited to share our latest papers accepted at @aclmeeting, @SIGIRConf, and beyond 🎉 From LLM reasoning and evaluation to multilingual NLP and fact-checking, there’s a lot we’ve been working on! Check them out 👇 More details and paper links coming soon 🔜
Sheffield NLP tweet media
English
1
6
27
1.7K
Sheffield NLP retweetledi
Atsuki Yamaguchi
Atsuki Yamaguchi@_gucciiiii·
Happy to announce that 3 papers have been accepted to #ACL2026 Main conference! Details in the subsequent posts. See you in San Diego! 🧷Note: I’m on the job market for Faculty/Research Fellow roles (starting April 2027)! Details here: gucci-j.github.io/about/ (1/3) #NLProc
Atsuki Yamaguchi tweet media
English
2
7
62
3.1K
Sheffield NLP
Sheffield NLP@SheffieldNLP·
🎉 SheffieldNLP at @eaclmeeting The main conference kicks off tomorrow, come say hello to our authors, we’d love to chat! 👋✨ @delvincezhang @miles_wil @nikaletras @casszzx @_joestacey_ P.S. Proud that EACL General Chair @AlineVillav is a Sheffield alum 🎓💖 #eacl2026
Sheffield NLP tweet media
Sheffield NLP@SheffieldNLP

🎉 New paper acceptances from Sheffield NLP! Our recent work has been accepted at @eaclmeeting , ECIR , and the CLEF Lab 🚀 Check out the poster for paper titles, authors, and links to available arXiv preprints 👇

English
0
1
11
801
Sheffield NLP retweetledi
Xi Wang
Xi Wang@wangxieric·
For our Sheffield NLP (@SheffieldNLP) seminar this week, we are delighted to have Chuan Meng (@ChuanMg) from the University of Edinburgh, sharing his research experience and his recent publication on revisiting text ranking in deep research.
Xi Wang tweet media
English
1
1
11
474
Sheffield NLP retweetledi
Xi Wang
Xi Wang@wangxieric·
A day to welcome Ingo and Libo @iFromm @Bertha0103 to Sheffield @SheffieldNLP for their OMINO UK tour on “Fake Science” and information overload in Academia.
Xi Wang tweet media
English
1
1
3
281
Sheffield NLP
Sheffield NLP@SheffieldNLP·
More #ICLR2026 good news from @SheffieldNLP 🎉 Alongside Cass’s papers, we’re excited to also have: "Attributing Response to Context: A Jensen–Shannon Divergence Driven Mechanistic Study of Context Attribution in RAG" by @wangxieric and collaborators arxiv.org/abs/2505.16415
Cass Zhixue@casszzx

Happy to share that two papers were accepted to #ICLR2026 🎉 A perfect cure for the Monday/January blues. Big shout-out to my amazing collaborators 🙌 1️⃣ PerSpectra: A Scalable and Configurable Pluralist Benchmark @lucie_nlp 2️⃣ Tracing and Reversing Edits @@SeifertChristin

English
0
0
5
436
Sheffield NLP
Sheffield NLP@SheffieldNLP·
Thanks to @peterbhase for a great seminar, a focused, informative overview of interpretability, CoT faithfulness, and controllable knowledge in LLMs🔍 (Posting a random mid-talk slide as proof it was packed with interesting content 😊)
Sheffield NLP tweet media
English
1
0
7
290
Sheffield NLP
Sheffield NLP@SheffieldNLP·
🎉 New paper acceptances from Sheffield NLP! Our recent work has been accepted at @eaclmeeting , ECIR , and the CLEF Lab 🚀 Check out the poster for paper titles, authors, and links to available arXiv preprints 👇
Sheffield NLP tweet media
English
0
2
12
1.6K

Keşfet

@suchirsalhan @macavaney @TerrierTeam @Xingwei__Tan @nikaletras @neural_avb @sandropezzelle @egrefen