Sheffield NLP
@SheffieldNLP
Followers
3K
Following
763
Media
47
Statuses
907
Established 1993, the University of Sheffield's #NLProc Group is one of the UK's largest natural language processing research centres.
Sheffield, UK
Joined November 2009
Big congratulations to Marco and co-authors for winning best resource paper award @emnlpmeeting #EMNLP2025 🔥☄️
Formalizing Complex Mathematical Statements with LLMs: A Study on Mathematical Definitions Lan Zhang, Marco Valentino (our upcoming Lecturer), Andre Freitas https://t.co/gbThlvFMLt
#EMNLP2025 Main
0
2
7
The #NLLP2025 workshop (at @emnlpmeeting
#EMNLP2025) is starting NOW — in-person & online! 🎉 It will be a full day packed with 38 great papers 🎥Tune in LIVE on our YouTube channel: https://t.co/TE2NibisFz 📅Schedule: https://t.co/PHOhayHwe6
#nllp #legaltech #nlproc
nllpw.org
The sixth workshop on Natural Legal Language Processing (NLLP 2024) explores methods and applications of Natural Language Processing for the Legal Domain by focusing on legal text and text with legal...
0
3
4
Great news!! Our scientific director Professor @kbontcheva of @sheffielduni / @SheffieldNLP has been appointed Chair of Working Group 1 for the new Code of Practice on the #Transparency of #AI Generated Content. https://t.co/W66t1LRWiB
veraai.eu
1
5
9
So excited for #EMNLP2025 ! We have some exciting papers at the conference, so come and check out our work & say hi to the team :) https://t.co/fAXuzNIKPM
🚀 Thrilled to share SheffieldNLP’s accepted papers at @emnlpmeeting #EMNLP2025! 🎉 Here’s a poster with (most of) them, a few more will be added soon! We’ll also highlight preprints in this thread as they appear ⬇️
0
4
14
Happy to share that our paper on extremely low-resource vocabulary expansion has been accepted to the prestigious Computational Linguistics journal @CompLingJournal🥳 Read the preprint: https://t.co/mL5OA7J5UM Work done with @AlineVillav & @nikaletras
arxiv.org
Large language models (LLMs) have shown remarkable capabilities in many languages beyond English. Yet, LLMs require more inference steps when generating non-English text due to their reliance on...
0
3
21
We are excited to announce that we are looking for PhD students for two projects funded by the EPSRC Doctoral Landscape Award! Both projects explore how we can make LLMs more reliable and trustworthy with respect to writing better code or supporting safe clinical decisions. 🧵
1
5
7
New CL paper on LLM vocabulary adaptation on extreme low resource languages 👇🏼
Happy to share that our paper on extremely low-resource vocabulary expansion has been accepted to the prestigious Computational Linguistics journal @CompLingJournal🥳 Read the preprint: https://t.co/mL5OA7J5UM Work done with @AlineVillav & @nikaletras
0
1
8
Funded PhD position available with me (and other supervisors) based in the School of Biosciences, looking at measuring impact of food systems chemicals on health. @sheffieldnlp @shefcompsci
findaphd.com
PhD Project - ECOSOLUTIONS DFA - IMEMRE: Development of an impact measurement (Immune, Emergence, Resistance) for food systems chemicals on human immune disease, infection and AMR at University of...
0
1
3
🚀 Fully funded PhD @SheffieldNLP Join our supportive NLP groups to explore AI safety & GenAI integrity 🧠💫 Meet me or @nikaletras at #EMNLP2025 I’ll be around the five papers when they are presenting, happy to chat about the PhD or life in Sheffield!
findaphd.com
PhD Project - Detection and Mitigation of Malicious Content Smuggling in GenAI Models (S3.5-COM-Zhao) at University of Sheffield, listed on FindAPhD.com
4
3
10
Congratulations to Dr. Ahmed Alajrami @aajrami who passed his PhD viva with minor corrections! Many thanks to the examiners Taher Pilehvar (Cardiff), @zhengyuan_nlp and @drmarkstevenson.
1
1
21
Check out @HuiyinXue 's new paper about deconstructing attention 🔥
📢📢Happy to share the work with @nikaletras and @NafiseSadat. 👉 https://t.co/bTf0BhDlO1 See👀 it, say🌐 it, upvote🔼 it! (1/2)
0
0
8
See Joe's google scholar for more information about his work:
scholar.google.com
University of Sheffield - Cited by 201 - Natural Language Processing
0
0
2
Welcome @_joestacey_ as our new postdoc! Great to hear your seminar today about improving the robustness of NLI models, and creating interpretable models using atomic inference. If you're interested in model robustness or creating interpretable models, check out Joe's work!
2
3
33
[📢 PhD / Visiting Student Opportunities] Hello world! I am looking for PhD students and visiting students at University of Sheffield. Details of the PhD opportunity can be found here:
findaphd.com
PhD Project - Retrieval-Augmented, Multi-Modal, and Explainable LLM for Fact-Checking at University of Sheffield, listed on FindAPhD.com
1
3
5
Just published in TMLR! 🚀 ElChat offers a more robust way to adapt chat LLMs to new languages using only unlabeled data. No base model needed. Better performance and chat abilities. 📄 https://t.co/2Z7sl5chPg Work done with @MorishTr @AlineVillav @nikaletras
#NLProc #TMLR
openreview.net
Vocabulary expansion (VE) is the de-facto approach to language adaptation of large language models (LLMs) by adding new tokens and continuing pre-training on target data. While this is effective...
1
6
24
Cool new work by @aajrami (w/ @Xingwei__Tan)! 👉🏼 Instruction-tuning on noisy instructions doesn't harm, and in some cases, improves LLM performance 👉🏼 LLMs don't really care about the instruction so much, they can infer what they should be doing from the input examples?
Training on messy instructions makes LLMs more robust and often better on clean prompts too. Llama 70B trained with 100% noisy instructions leads BBH under noisy tests, and also reaches the top on MMLU. The problem is that small wording changes can flip answers even when
1
3
13
CORRECT: Context- and Reference-Augmented Reasoning and Prompting for Fact-Checking: https://t.co/doMvZ4mUUs and Unmasking Fake Careers: Detecting Machine-Generated Career Trajectories via Multi-layer Heterogeneous Graphs https://t.co/8oZkjU9xW3
0
0
3
We had a brilliant seminar by @delvincezhang today to kick off our new seminar series, looking at fact-checking with structured and unstructured information. Delvin's a new lecturer here with us at Sheffield 😀 Links to his fact-checking papers are below 👇
1
1
10
🚨Call for Demos at EACL 2026 @eaclmeeting is open! Showcase your NLP system, from prototype to production, with a demo video + live site or installable package. 📅 Deadline: 1 Dec 2025 🔗 https://t.co/I8SL1nXdaz
#NLP #EACL2026 #DemoTrack w/ Danilo Croce & @jochenleidner
0
3
17
🚨 Deadline update: Direct submissions ➡️ Oct 6 ARR commitment ➡️ Oct 27 ARR July meta-reviews drop tomorrow. Disappointed? Got a relevant paper? Aim it at #SciProdLLM
https://t.co/Yyj9GX2LbM
#AI4Science @aaclmeeting #AACL2025
🚨Call for Papers SciProdLLM 2025 explores human-centered use of LLMs in science, from idea generation to peer review Submit your work on LLM-assisted research workflows, evaluation, and co-authorship Deadline: Sept 29 https://t.co/pgl4IKDmgL
#AI4Science #AACL2025 @aaclmeeting
0
1
3