Webis Group

413 posts

Webis Group banner
Webis Group

Webis Group

@webis_de

Research group working the fields of Information Retrieval, Natural Language Processing, Data Mining, Machine Learning, and Artificial Intelligence.

Hannover/Jena/Leipzig/Weimar Katılım Eylül 2019
385 Takip Edilen741 Takipçiler
Webis Group
Webis Group@webis_de·
For full technical details + compliance Datasheet see our preprint @ arxiv.org/abs/2510.13996 As for German-specific models trained on this data... stay tuned 👀
English
0
0
6
215
Webis Group
Webis Group@webis_de·
The data spans 7 text domains: 🌐 Web: Wikis, GitHub, social media 💬 Political: Parliamentary proc., speeches ⚖️ Legal: Court decisions, law 📰 News: Newspaper archives 🏦 Economics: Public tenders 📚 Cultural: Heritage collections 🔬 Scientific: Papers, books, journals
Webis Group tweet media
English
1
0
6
272
Webis Group
Webis Group@webis_de·
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…
English
3
18
89
19.3K
Webis Group
Webis Group@webis_de·
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_ax… Nice to see axiomatic IR gaining momentum.
Webis Group tweet media
Padua, Veneto 🇮🇹 English
1
5
15
576
Webis Group
Webis Group@webis_de·
Come join us at the poster session at ICTIR 2025 to discuss: - Axioms for Retrieval-Augmented Generation #merker_2025b" target="_blank" rel="nofollow noopener">webis.de/publications.h… - Learning Effective Representations for Retrieval Using Self-Distillation with Adaptive Relevance Margins #gienapp_2025b" target="_blank" rel="nofollow noopener">webis.de/publications.h…
Webis Group tweet media
Padua, Veneto 🇮🇹 English
1
1
7
447
Webis Group
Webis Group@webis_de·
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. 📄 #gienapp_2025a" target="_blank" rel="nofollow noopener">webis.de/publications.h…
Webis Group tweet media
English
1
6
20
555
Webis Group
Webis Group@webis_de·
@LukasGienapp presents "The Viability of Crowdsourcing for RAG Evaluation" at #SIGIR2025 The paper is available at: #gienapp_2025a" target="_blank" rel="nofollow noopener">webis.de/publications.h…
Webis Group tweet mediaWebis Group tweet media
Padua, Veneto 🇮🇹 English
0
2
8
186
Webis Group retweetledi
Maik Fröbe
Maik Fröbe@maik_froebe·
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
Maik Fröbe tweet media
English
0
7
14
578
Webis Group
Webis Group@webis_de·
Results on BEIR demonstrate that our method matches teacher distillation effectiveness, while using only 13.5% of the data and achieving 3-15x training speedup. This makes effective bi-encoder training more accessible, especially for low-resource settings.
Webis Group tweet media
English
1
0
0
91
Webis Group
Webis Group@webis_de·
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.
Webis Group tweet media
English
1
2
6
278
Webis Group retweetledi
Ferdinand Schlatt
Ferdinand Schlatt@fschlatt1·
@maik_froebe @hscells @ShengyaoZhuang @bevan_koopman @guidozuc @bennostein @martinpotthast @matthias_hagen Short: Rank-DistiLLM: Closing the Effectiveness Gap Between Cross-Encoders and LLMs for Passage Re-ranking #schlatt_2025c" target="_blank" rel="nofollow noopener">webis.de/publications.h… Full: Set-Encoder: Permutation-Invariant Inter-Passage Attention for Listwise Passage Re-Ranking with Cross-Encoders #schlatt_2025b" target="_blank" rel="nofollow noopener">webis.de/publications.h…
Ferdinand Schlatt tweet media
English
0
7
29
961