Carolin Holtermann (@CarolinHolterm) profile picture

PhD Student at the Data Science Chair in Hamburg

Hamburg, Germany
Joined December 2021
Photo by Carolin Holtermann (@CarolinHolterm)Photo by Carolin Holtermann (@CarolinHolterm)Photo by Carolin Holtermann (@CarolinHolterm)Photo by Carolin Holtermann (@CarolinHolterm)Photo by Carolin Holtermann (@CarolinHolterm)
🧠 Which knowledge module do I need and how much of it ⁉️ 🌟 Check out our latest paper, "What the Weight?! A Unified Framework for Zero-Shot Knowledge Composition", which has been officially accepted for Findings of the EACL Conference! arxiv.org/pdf/2401.12756.pdf
4
1
1
11
1,101
🚨 New paper alert: A new generation of LLMs can now process speech natively. This could expand access for millions excluded by text interfaces, but our research shows a cost: demographic cues in speaker voice can trigger stereotypical model responses. 🎙️⚖️
3
6
3
19
3,832
A huge thank you to all the amazing authors of this work!! ✨@minhducbui_nlp @KaitlynZhou @vjhofmann @kelina1124 @anne_lauscher
3
99
🛠️ Study 3: Mitigation exists. Discrimination tracks continuously with vocal pitch. Systematically lowering pitch reduced bias to statistically insignificant levels across all tested models.
1
1
74
🚨The result is a self-reinforcing gap: systems optimize for frequent users, while growing more distant from those they were supposed to reach. Fairness and accessibility have to be tackled together.
1
59
📣 CFP: Eval4SD @ KONVENS 2026, Hamburg (Sept 14–17) 1st workshop on evaluating LLMs for specialized domains. We invite work on benchmarking, replication, and evaluation methodology across diverse fields. Deadline: Jul 3, 2026, 23:59 CEST eval4sd.github.io/
6
72
✨Preprint Alert ✨ Thrilled to share that our paper has been accepted at the #EMNLP2025 main conference! 🚨 We uncover harmful stereotypical biases in LLMs toward German dialect speakers. 🚨 Check out the paper: arxiv.org/abs/2509.13835 Many thanks to all the great authors! 🙌🏼
"You speak Bavarian? Then you must be uneducated and closed-minded!" 🤯 Not your opinion? Good. But it might be your LLM's! 🧵 In our #EMNLP2025 paper we uncover concerning dialect bias in recent LLMs - including GPT-5. #AI #Bias #Dialect #Fairness #LLM #NLProc #Safety
4
90
📣 I am looking for a new Ph.D. student! 📣 The position is part of a @DASHHPhD project on (multimodal) #LLMs for laser operations with me (@DS_research_HH @unihh) and @HTuennermann from @desy. Deadline: October 20th! Feel free to reach out! 🚀🛸💥 dashh.org/application/phd_to…
66
2
140
15,193
Carolin Holtermann retweeted
🎉 We are happy to announce that the Data Science Lab Hamburg has 4 papers accepted at the #acl2024 in Bangkok🇹🇭! @KatiaShutova @anne_lauscher @CarolinHolterm @FrohmannM @manuellardelli @peppeatta @paul_rottger
4
17
623
Carolin Holtermann retweeted
📢Hi X Community! We are the #datascience research group led by @anne_lauscher in Hamburg! We are doing #NLProc research relating to various topics such as #LLMs, multimodality, #EthNLP, etc. Follow our new account if you are interested in latest results, insights, and more! 📢
4
9
873
Carolin Holtermann retweeted
🎉 Our paper "ScaLearn: Simple and Highly Parameter-Efficient Task Transfer by Learning to Scale" has been accepted to #ACL2024 findings! Congrats to my amazing co-authors @CarolinHolterm, Shahed Masoudian, @anne_lauscher, Navid Rekabsaz!
Preprint alert! 🚨 📢 Announcing… ScaLearn! Redefining the landscape of Multi-task Learning (MTL) in NLP. Dive in to see how our ScaLearn enables highly efficient task transfer using adapters! 🚀 Spoiler: 8 parameters may be all you need. 🤯
2
7
464
I recently gave a talk on fairness & inclusion in #LLMs at the annual meeting of @IT_Frauen of @informatikradar. Here, I present insights from our recent work lead by @CarolinHolterm & @paul_rottger. Thanks to @ada_gelie for the picture! #NLProc
3
41
1,406
📅We're excited to present our Findings paper in a poster Session at the EACL Main Conference and additionally in an oral presentation at the MOOMIN (moomin-workshop.github.io/cf…) Workshop! @eaclmeeting
2
126
(2/2) Focusing on the scenario of domain knowledge and adapter layers, our framework provides a systematic unification of concepts, allowing us to conduct the first comprehensive benchmarking study of various zero-shot knowledge composition strategies.
99
(1/2)🔍In this work, we delve into the possibilities of combining knowledge by proposing a novel framework for zero-shot module composition, which encompasses existing and some novel variations for selecting, weighting, and combining parameter modules under a unified notion.
95