@martin-potthast.com
Professor at the University of Kassel, https://hessian.AI, and https://ScaDS.AI. Member of @webis.de Research in information retrieval #IR, natural language processing #NLP, and artificial intelligence.
I think this is perfectly alright.
A bit of show and tell is just what we need in order to collect enough observations until eventually someone is inspired to conduct "the next Cranfield experiments" that show us the new optimization goal the community can get behind as a whole.
Post a pic you took, no context, to bring some zen to the feed.
I'd hope for a revival of StackExchange.
No cheating, repost the most recent picture of your pet(s)
I'm thinking in a similar direction. I keep asking myself: How can we reliably establish human influence, effort, or sincerity in a digital object, which could have also been generated?
Thesis: Authenticity checks will replace part of the time savings of GenAI.
Before quality of writing sufficed.
🧑🔬I’m recruiting PhD students in Natural Language Processing @unileipzig.bsky.social Computer Science, together with @scadsai.bsky.social!
Topics include, but aren’t limited to:
🔎Linguistic Interpretability
🌍Multilingual Evaluation
📖Computational Typology
Please share!
#NLProc #NLP
Seconded.
If it needs to be separate from other situations where induction occurs, then maybe:
In-context induction, though that does not differentiate it too well from the model's inference run itself.
Maybe: Inductive prompting?
We just released "German Commons", the largest openly-licensed German text dataset for LLM training: 154B tokens with clear usage rights for research and commercial use.
huggingface.co/datasets/coral-nlp/german-commons
ChatGPT gives you little to no predictability of results in how your text changes. Grammarly and DeepL do.
🌟Really excited to share the fourth Strategic Workshop on Information Retrieval (SWIRL) report published in SIGIR Forum!
Paper 👉🏻 www.johannetrippas.com/papers/tripp...
More info 👉🏻 sites.google.com/view/swirl20...
#SWIRL2025 #SIGIR2026 #IR #GenAI #Research #CHIIR2026
Thrilled to announce that Matti Wiegmann has successfully defended his PhD! 🎉🧑🎓 Huge congratulations on this incredible achievement! #PhDDefense #AcademicMilestone
Honored to win the ICTIR Best Paper Honorable Mention Award for "Axioms for Retrieval-Augmented Generation"!
Our new axioms are integrated with ir_axioms: github.com/webis-de/ir_...
Nice to see axiomatic IR gaining momentum.
We presented two papers at ICTIR 2025 today:
- Axioms for Retrieval-Augmented Generation webis.de/publications...
- Learning Effective Representations for Retrieval Using Self-Distillation with Adaptive Relevance Margins webis.de/publications...
Want to know how to make bi-encoders more than 3x faster with a new backbone encoder model? Check out our talk on the Token-Independent Text Encoder (TITE) #SIGIR2025 in the efficiency track. It pools vectors within the model to improve efficiency dl.acm.org/doi/10.1145/...
Now @fschlatt.bsky.social presents "TITE: Token-Independent Text Encoder for Information Retrieval" at #SIGIR2025
Paper: webis.de/publications...
Here are some impressions from our ReNeuIR workshop on "Reaching Efficiency in Neural IR" that we had yesterday at #SIGIR2025.
Happy to share that our paper "The Viability of Crowdsourcing for RAG Evaluation" received the Best Paper Honourable Mention at #SIGIR2025! Very grateful to the community for recognizing our work on improving RAG evaluation.
📄 webis.de/publications...
Lukas Gienapp presents "The Viability of Crowdsourcing for RAG Evaluation" at #SIGIR2025
The paper is available at: webis.de/publications...
@mrparryparry.bsky.social presenting our work on reproducing TREC DL 2019 judgements and the implications for evaluating modern ranking models on modern collections. Paper: arxiv.org/abs/2502.20937
Thank you Carlos for the shout-out of Lightning IR in the LSR tutorial at #SIGIR2025
If you want to fine your own LSR models, check out our framework at github.com/webis-de/lig...
From July 13-17, 2025, @scadsai.bsky.social will join the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval in Padua, Italy. Our researchers have made the following contributions.
Learn more about #SIGIR2025:
👉 https://sigir2025.dei.unipd.it/
Dory from finding nemo with the quote: "I remember it like it was yesterday. Of course, I dont remember yesterday."
Do not forget to participate in the #TREC2025 Tip-of-the-Tongue (ToT) Track :)
The corpus and baselines (with run files) are now available and easily accessible via the ir_datasets API and the HuggingFace Datasets API.
More details are available at: trec-tot.github.io/guidelines
Our paper on self-distillation for training bi-encoders got accepted at #ICTIR2025! By exploiting pretrained encoder capabilities, our approach eliminates expensive teacher models and batch sampling while maintaining the same effectiveness.
Most reporting on AI examines worst-case systems deployed under the guise of efficiency. But what would a good faith effort at Ethical AI look like? For two years, we’ve been looking over the shoulder of a city trying to do things differently.
All @acm.org publications will be 100% Open Access as of January 2026. When we announced this at POPL and CHI this year, conference participants spontaneously erupted in applause. The CS community is excited about ACM's move to OA!
The deadline for submissions to the ReNeuIR workshop at #SIGIR2025 is extended to June 10 😸
Details: reneuir.org
#ReNeuIr2025 #SIGIR25
PAN 2025 Call for Participation: Shared Tasks on Authorship Analysis, Computational Ethics, and Originality
We'd like to invite you to participate in the following shared tasks at PAN 2025 held in conjunction with the CLEF conference in Madrid, Spain.
Find out more at pan.webis.de/clef25/pan25...
We share your concern that LLMs could be prompted to generate responses that are biased in favor of certain products. That is why we are currently organizing a shared task on detecting advertisements in the responses of RAG-based search engines: bsky.app/profile/webi...
Teaser Image: The text says ReNeuIR’25 - Workshop on Reaching Efficiency in Neural Information Retrieval
The fourth edition of ReNeuIR @ #SIGIR2025 is back!! Check reneuir.org to see what we have in mind this year! Paper submission deadline: May 20, 2025.
Can LLM-generated ads be blocked? With OpenAI adding shopping options to ChatGPT, this question gains further importance.
If you are interested in contributing to the research on LLM-based advertising, please check out our shared task: touche.webis.de/clef25/touch...
More details below.