SheffieldNLP

🚨 Happy to share some recently accepted papers from our group.
They cover a range of topics, from reasoning and hallucination mitigation to dialogue evaluation, bias, humour generation, and more 📚✨
If you’d like to take a look, the arXiv links are in the poster.

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 Sheffield on Find... 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 She...

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.bsky.social @shefcmi.bsky.social
findaphd.com/phds/project...

Kalina Bontcheva Appointed Chair of EU Working Group on AI Transparency VERification Assisted by AI. R&D & innovation co-funded by the HorizonEU. Continuing WeVerify work. And much more!

Great news!! Our scientific director Professor Kalina Bontcheva @sheffieldnlp.bsky.social at @sheffielduni.bsky.social has been appointed Chair of Working Group 1 for the new Code of Practice on the #Transparency of #AI -Generated Content.
www.veraai.eu/posts/kalina...

Delvin Ce Zhang Delvin Ce Zhang

🎉 A warm welcome to Delvin Ce Zhang who recently joined us as a Lecturer!

His research applies Multi-Modal LLMs to real-world tasks like misinformation detection, recommender systems, and AI for science. Excited to have him on board and for many collaborations! 🌺🚀
sites.google.com/view/delvinc...

Comparing Apples to Oranges: A Dataset & Analysis of LLM Humour Understanding from Traditional Puns to Topical Jokes Humour, as a complex language form, is derived from myriad aspects of life, whilst existing work on computational humour has focussed almost exclusively on short pun-based jokes. In this work, we inve...

Comparing Apples to Oranges: A Dataset & Analysis of LLM Humour Understanding from Traditional Puns to Topical Jokes

Tyler Loakman, William Thorne, Chenghua Lin
arxiv.org/abs/2507.13335
#EMNLP2025 Findings

GreekBarBench: A Challenging Benchmark for Free-Text Legal Reasoning and Citations We introduce GreekBarBench, a benchmark that evaluates LLMs on legal questions across five different legal areas from the Greek Bar exams, requiring citations to statutory articles and case facts. To ...

GreekBarBench: A Challenging Benchmark for Free-Text Legal Reasoning and Citations

Odysseas Chlapanis, Dimitrios Galanis, Nikos Aletras, Ion Androutsopoulos
arxiv.org/abs/2505.17267
#EMNLP2025 Findings

Enhancing Logical Reasoning in Language Models via Symbolically-Guided Monte Carlo Process Supervision Large language models (LLMs) have shown promising performance in mathematical and logical reasoning benchmarks. However, recent studies have pointed to memorization, rather than generalization, as one...

Enhancing Logical Reasoning in Language Models via Symbolically-Guided Monte Carlo Process Supervision

Xingwei Tan, Marco Valentino, Mahmud Elahi Akhter, Maria Liakata, Nikos Aletras
arxiv.org/abs/2505.20415
#EMNLP2025 Main

How Private are Language Models in Abstractive Summarization? In sensitive domains such as medical and legal, protecting sensitive information is critical, with protective laws strictly prohibiting the disclosure of personal data. This poses challenges for shari...

How Private are Language Models in Abstractive Summarization?

Anthony Hughes, Ning Ma, Nikos Aletras
arxiv.org/abs/2412.12040
#EMNLP2025 Main

Beyond Hate Speech: NLP's Challenges and Opportunities in Uncovering Dehumanizing Language Dehumanization, i.e., denying human qualities to individuals or groups, is a particularly harmful form of hate speech that can normalize violence against marginalized communities. Despite advances in ...

Beyond Hate Speech: NLP’s Challenges and Opportunities in Uncovering Dehumanizing Language

Hamidreza Saffari, Mohammadamin Shafiei, Hezhao Zhang, Lasana T. Harris, Nafise Sadat Moosavi
arxiv.org/abs/2402.13818
#EMNLP2025 Main

Does Multimodal Large Language Model Truly Unlearn? Stealthy MLLM Unlearning Attack Multimodal Large Language Models (MLLMs) trained on massive data may memorize sensitive personal information and photos, posing serious privacy risks. To mitigate this, MLLM unlearning methods are pro...

Does Multimodal Large Language Model Truly Unlearn? Stealthy MLLM Unlearning Attack

Xianren Zhang, Hui Liu, Delvin Ce Zhang, Xianfeng Tang, Qi He, Dongwon Lee, Suhang Wang
www.arxiv.org/abs/2506.17265
#EMNLP2025 Main

Label Set Optimization via Activation Distribution Kurtosis for Zero-shot Classification with Generative Models In-context learning (ICL) performance is known to be sensitive to the prompt design, yet the impact of class label options in zero-shot classification has been largely overlooked. This study presents ...

Label Set Optimization via Activation Distribution Kurtosis for Zero-Shot Classification with Generative Models

Yue Li, Zhixue Zhao, Carolina Scarton
arxiv.org/abs/2410.19195
#EMNLP2025 Main

Beyond the Score: Uncertainty-Calibrated LLMs for Automated Essay Assessment

Ahmed Karim, Qiao Wang, Zheng Yuan
openreview.net/forum?id=UiW...
#EMNLP2025 Main

Formalizing Complex Mathematical Statements with LLMs: A Study on Mathematical Definitions Thanks to their linguistic capabilities, LLMs offer an opportunity to bridge the gap between informal mathematics and formal languages through autoformalization. However, it is still unclear how well ...

Formalizing Complex Mathematical Statements with LLMs: A Study on Mathematical Definitions

Lan Zhang, Marco Valentino (our upcoming Lecturer), Andre Freitas
arxiv.org/abs/2502.12065
#EMNLP2025 Main

🚀 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 ⬇️

Heading to #ACL2025NLP this weekend? Don’t miss the amazing work from SheffieldNLP!

Check them out & come chat with us in Vienna! 🇦🇹👋📰

Our annual #conference is now less than 5 weeks away!

Join us on 23 June in sunny #Sheffield to hear about our #PhD students’ #AI and #ML #speech and #NLProc research! Check out our website for more info!

slt-cdt.sheffield.ac.uk/annual-confe...

Congratulations to Edward Gow-Smith on passing his #PhD #viva with minor corrections! Huge thanks to his supervisor @alinevillav.bsky.social and his viva examiners Professor Dr Hinrich Schütze (@cislmu.bsky.social) and Dr Nafise Sadat Moosavi (University of Sheffield)!

Great day out in the Peaks for our Research Away Day just outside Sheffield! 🚍☕🌲
Inspiring talks, thoughtful discussions, and plenty of time to connect. Thanks to all who joined and made it special!🌺

Excited to share the list of SheffieldNLP accepted papers at @aclmeeting.bsky.social @icmlconf.bsky.social @SIGIRlist.idf.social.ap.brid.gy

Congrats to all authors, especially our first-time PhD presenters! 🎉
Thread coming soon with details on each paper!

We're delighted to host Prof. Steffen Eger for an insightful talk on "Multimodal Scientific Content Generation with LLMs", covering tools like AutomaTikz, DeTikZify, and ScImage that aim to automate and enhance scientific figure generation🤖📚

Last few days to get your application in for one of our two fully-funded 3.5 year #AI #PhD studentships in #spoken #language #technologies available for Sept 2025 start!

** Apply now! Deadline: 13 Apr 2025 **

slt-cdt.sheffield.ac.uk/apply

#speech #nlp #nlproc #research #sheffield

Applications for two affiliated fully-funded 3.5 year #spoken #language #technologies #AI #PhD studentships open!

Join us! Sept 2025 start!

** Apply now! Deadline: 13 Apr 2025 **

slt-cdt.sheffield.ac.uk/apply

#speech #nlp #nlproc #research #sheffield

Zheng Yuan ‪Assistant Professor, King’s College London; Visiting Researcher, University of Cambridge‬ - ‪‪Cited by 1,649‬‬ - ‪NLP‬ - ‪EdTech‬ - ‪Educational NLP‬ - ‪CALL‬

We are thrilled to welcome Zheng Yuan (raise your hand Zheng if you are here :) to our group as the new Senior Lecturer in NLP! We are very much looking forward to learning from and collaborating with her😊
Welcome aboard😊🌺
scholar.google.co.uk/citations?us...

🚀 Reminder! 🚀

The deadline for the Postdoc in Uncertainty Quantification for Foundation Models at SheffieldNLP with Nafise, Benjamin, and Kentaro is March 2nd—just a few days left! 🗓️
📆 Initial contract: 12 months (with a possibility of an additional 2-year extension)

We were honored to host @ekdeepl.bsky.social at the SheffieldNLP seminar for an exciting talk on the Dynamics of Concept Learning & Emergent Abilities in Neural Networks😊Great insights on how scaling impacts sudden capability learning, structured representations & in-context learning🔥🚀

Research Associate in Quantitative and Computational Social Science Methods at University of Sheffield Searching for an academic job? Explore this Research Associate in Quantitative and Computational Social Science Methods opening on jobs.ac.uk! Click to view more details and browse other academic jobs...

Come and work with us! We have a part-time RA post on Computational Social Science / Journalism looking at data on abuse against journalists. Please share widely. jobs.ac.uk/job/DLU035/r... @sheffieldnlp.bsky.social

As many areas, science itself will be transformed by AI. We have now released a state-of-the-art survey on this emerging field. We discuss methods and tools for AI-enhanced search, ideation, experimentation, content generation and peer review.
arxiv.org/pdf/2502.05151

Research Associate in Uncertainty Quantification for Foundation Models at University of Sheffield Recruiting now: Research Associate in Uncertainty Quantification for Foundation Models on jobs.ac.uk. Click for details and explore more academic job opportunities on the top job board

🚀 Postdoc Opportunity! 🚀
Nafise Sadat Moosavi, with Benjamin Heinzerling (@RIKEN) & Kentaro Inui, are hiring a Postdoc for Uncertainty Quantification in Foundation Models—primarily in Sheffield, with a chance to visit RIKEN, Japan!
Deadline: 2 March
More info: www.jobs.ac.uk/job/DLS026/r...

Our colleague @xiwang-sch.bsky.social was on leave, and we missed his papers in our original list! Now, here’s the full, updated set of SheffieldNLP’s accepted papers at NAACL, ICLR, ECIR, and WWW! 😊✨

Exploring NLP Applications in Food Research: my ATRIUM TNA visit to the GATE group By Tenia Panagiotou As a postdoctoral researcher at the Consumer and Sensory Lab of the Department of Food Science and Nutrition of the Univ...

A lovely report from our latest @atrium-eu.bsky.social
#TNA visitor Tenia about her research visit to our GATE
team @sheffieldnlp.bsky.social to study NLP applications in food research.
gate4ugc.blogspot.com/2025/02/expl...