Lightnews — Scholar-powered news

MaiNLP lab, LMU Munich @mainlp.bsky.social · Aug 11

Awesome! We're also creating one currently and have included yours as a starter :)

Reposted by MaiNLP lab, LMU Munich

Verena Blaschke @verenablaschke.bsky.social · Aug 7

At #Interspeech2025 I'm going to present Betthupferl, a dataset for German dialect ASR & dialect-to-standard speech translation! We analyze differences between dialectal & Standard German transcriptions, benchmark ASR models, and examine shortcomings of current ASR models & evaluation metrics.

Piper title ("A multi-dialectal dataset for German dialect ASR and dialect-to-standard speech translation") and a map of the German state Bavaria showing where the Franconian, Bavarian, and Alemannic dialect groups are spoken

1 4 16

Reposted by MaiNLP lab, LMU Munich

Verena Blaschke @verenablaschke.bsky.social · Jul 27

UPDATE: Our poster presentation got moved to Tuesday, 16:00–17:30 (session 10)! #ACL2025NLP

Verena Blaschke @verenablaschke.bsky.social · Jul 18

At #ACL2025NLP I'll present our analysis of the effect of linguistic similarity on cross-lingual transfer! We looked at how 10 similarity measures correlate w/ transfer results btwn 263 languages across 3 NLP tasks. Different similarity measures matter for diff. experiments (no one-size-fits-all)!

Correlations between transfer results per experiment (parsing, POS tagging, topic classification with different input representations) and similarity measures. The results vary a lot across experiments and measures – some are described in the next posts.

1 3

MaiNLP lab, LMU Munich @mainlp.bsky.social · Jul 27

Unsure which presentations to attend at #ACL2025? 🛎️🗣️

MaiNLP lab, LMU Munich @mainlp.bsky.social · Jul 23

Headed to ACL? MaiNLP & our most recent work will be there too👥📄
Come see what we’ve been working on!

2 4

MaiNLP lab, LMU Munich @mainlp.bsky.social · Jul 23

👥‪ @boleima.bsky.social Yuting Li, Wei Zhou, Ziwei Gong, @janetlauyeung.bsky.social Katja Jasinskaja @annefriedrich.bsky.social Julia Hirschberg, Frauke Kreuter @barbaraplank.bsky.social

MaiNLP lab, LMU Munich @mainlp.bsky.social · Jul 23

👥‪ @boleima.bsky.social Berk Yoztyurk @carohaensch.bsky.social @xinpeng.bsky.social Markus Herklotz, Frauke Kreuter @barbaraplank.bsky.social @assenmacher.bsky.social

1

MaiNLP lab, LMU Munich @mainlp.bsky.social · Jul 23

📝 Analyzing the Effect of Linguistic Similarity on Cross-Lingual Transfer: Tasks and Experimental Setups Matter
🔎 263 languages, 10 similarity measures, 3 NLP tasks
👥 @verenablaschke.bsky.social Masha Fedzechkina @maartjeterhoeve.bsky.social
🔗 arxiv.org/abs/2501.14491
📁 Findings – long

MaiNLP lab, LMU Munich @mainlp.bsky.social · Jul 23

📝Do LLMs Give Psychometrically Plausible Responses in Educational Assessments?
🔎Analyzing how human-like LLMs are when taking reading, history, and economics tests
👥 @saeub.bsky.social , Diego Frassinelli, @barbaraplank.bsky.social
🔗 arxiv.org/abs/2506.09796
📁BEA workshop - Long

1 1 2

MaiNLP lab, LMU Munich @mainlp.bsky.social · Jul 23

📝 GerMedIQ: A Resource for Simulated and Synthesized Anamnesis Interview Responses in German
🔎 We release a novel German anamnesis question-response dataset with human-simulated and LLM-augmented responses.
👥 @JHofenbitzer et al.
🔗 github.com/Jhofenbitzer...
📁SRW - Long

1

MaiNLP lab, LMU Munich @mainlp.bsky.social · Jul 23

📝Probing LLMs for Multilingual Discourse Generalization Through a Unified Label Set
🔎Do LLMs encode and generalize discourse knowledge across languages?
👥 @florian-eichin.com @janetlauyeung.bsky.social @mhedderich.bsky.social @barbaraplank.bsky.social
🔗 arxiv.org/abs/2503.10515
📁Main - Long

1 1 3

MaiNLP lab, LMU Munich @mainlp.bsky.social · Jul 23

📝LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks
🔎We present a large-scale study of whether LLM judgments can be reliably used as proxies for human judgments
👥Anna Bavaresco et al.
🔗 arxiv.org/abs/2406.18403
📁Main - Short

1

MaiNLP lab, LMU Munich @mainlp.bsky.social · Jul 23

📝 What's the Difference? Supporting Users in Identifying the Effects of Prompt and Model Changes Through Token Patterns
👥 @mhedderich.bsky.social Anyi Wang @raoyuan.bsky.social @florian-eichin.com Jonas Fischer @barbaraplank.bsky.social  
🔗 arxiv.org/abs/2504.158... 
📁Main - Long

1 1 2

MaiNLP lab, LMU Munich @mainlp.bsky.social · Jul 23

📝A Rose by Any Other Name: LLM-Generated Explanations Are Good Proxies for Human Explanations to Collect Label Distributions on NLI
👥 @beiduo.bsky.social Siyao Peng @annakorhonen.bsky.social @barbaraplank.bsky.social
🔗 arxiv.org/abs/2412.13942
📁ACL25 Findings-Long

1

MaiNLP lab, LMU Munich @mainlp.bsky.social · Jul 23

📝Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models
🔎We study the relationship between circuits for highly compositional and functionally related tasks
👥@pmondorf.bsky.social Sondre Wold @barbaraplank.bsky.social
🔗 arxiv.org/abs/2410.01434
📁Main-Long

1

MaiNLP lab, LMU Munich @mainlp.bsky.social · Jul 23

📝Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challenges
🔎We review existing datasets for evaluating LLMs’ pragmatic capabilities, outlining key challenges and promising future directions
🔗 arxiv.org/abs/2502.12378
📁Main - Long

2

MaiNLP lab, LMU Munich @mainlp.bsky.social · Jul 23

📝Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Study
🔎This study evaluates LLMs in generating German public opinions using open-ended survey data
🔗 arxiv.org/abs/2412.13169
📁Main - Long

2

MaiNLP lab, LMU Munich @mainlp.bsky.social · Jul 23

Headed to ACL? MaiNLP & our most recent work will be there too👥📄
Come see what we’ve been working on!

1 5 14

Reposted by MaiNLP lab, LMU Munich

Philipp Mondorf @pmondorf.bsky.social · Jul 18

📄 [ACL 2025 main] Circuit compositions: Exploring Modular Structures in Transformer-Based Language Models (doi.org/10.48550/arX...)

Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models

A fundamental question in interpretability research is to what extent neural networks, particularly language models, implement reusable functions through subnetworks that can be composed to perform mo...

doi.org

1 2 5

Reposted by MaiNLP lab, LMU Munich

Philipp Mondorf @pmondorf.bsky.social · Jul 18

📄 [ACL 2025 main] LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks (doi.org/10.48550/arX...)

LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks

There is an increasing trend towards evaluating NLP models with LLMs instead of human judgments, raising questions about the validity of these evaluations, as well as their reproducibility in the case...

doi.org

1 4 9

Reposted by MaiNLP lab, LMU Munich

Verena Blaschke @verenablaschke.bsky.social · Jul 18

At #ACL2025NLP I'll present our analysis of the effect of linguistic similarity on cross-lingual transfer! We looked at how 10 similarity measures correlate w/ transfer results btwn 263 languages across 3 NLP tasks. Different similarity measures matter for diff. experiments (no one-size-fits-all)!

1 1 21

Reposted by MaiNLP lab, LMU Munich

Bolei Ma @boleima.bsky.social · Jul 16

🤔 Can LLMs read between the lines?

Our another #ACL2025 paper surveys resources on how LLMs handle pragmatics like implicatures, deixis, and more. We map out a new landscape for both LLMs and linguistics in pragmatic research.

📄 arxiv.org/abs/2502.12378
🧠💬 #LLMs #Pragmatics

1 4 16

Reposted by MaiNLP lab, LMU Munich

Beiduo Chen @beiduo.bsky.social · Jul 15

🚨 Can LLMs generate explanations that are as useful as human ones for modeling label distributions in NLI?🌹"A Rose by Any Other Name" shows that they can
💬 We explore scalable, explanation-based annotation via LLMs.
📍Come find us in Vienna 🇦🇹! (July 28, 18:00-19:30, Hall 4/5) #ACL2025NLP #acl2025

3 1 4

Reposted by MaiNLP lab, LMU Munich

Bolei Ma @boleima.bsky.social · Jul 14

🎉 Our paper “Algorithmic Fidelity of LLMs in Generating Synthetic German Public Opinions” is accepted at #ACL2025 main conference as an oral presentation! 🇩🇪🤖

We study how well LLMs simulate real survey responses using open-ended German data, showing the left-leaning bias.

1 1 4

MaiNLP lab, LMU Munich @mainlp.bsky.social · Jul 11

The future of AI literacy starts early! Our very own @fkoerner.bsky.social recently led a series of hands-on workshops teaching some of our youngest students yet 🌱🤖

Feliçia Körner @fkoerner.bsky.social · Jul 11

Had the pleasure of leading AI workshops with @munichcenterml.bsky.social‬ for 2nd- and 3rd-graders in late June!

Designing the material was a fun challenge, and I've never had a more curious audience. Here we explored MT (had to stay true to my roots); check out what they wanted to translate!

An instructor stands in front of a projected screen showing Google Translate translating the sentence "good night good night, don't let the bed bugs bite" to German

3

Reposted by MaiNLP lab, LMU Munich

Michael A. Hedderich @mhedderich.bsky.social · Jul 11

Looking forward to my visit to Hamburg University and their Data Science group!

Data Science Hamburg Group @ds-hamburg.bsky.social · Jul 11

Our group is launching a monthly seminar series! Next week, we will have @mhedderich.bsky.social from LMU Munich, who will give a talk at our seminar.

Date: July 16
Time: 10.00 - 11.30 am CET

You can either attend the seminar via Zoom or in-person. Register here if you are interested.

University of Hamburg Data Science Group Seminar

This is the signup form for University of Hamburg Group Seminar. Please fill your details in here. You will be sent the zoom link a few hours before the lecture, if your details are valid. Details fo...

docs.google.com

1 3