@H1iReimer @maik_froebe @martinpotthast @matthias_hagen @bennostein Congratulations to the authors @H1iReimer, @maik_froebe, @bennostein, @martinpotthast, @matthias_hagen from @UniJena, @bauhaus_uni, @uni_kassel, @Hessian_AI, @Sca_DS!.

Honored to win the ICTIR Best Paper Honorable Mention Award for "Axioms for Retrieval-Augmented Generation"!.Our new axioms are integrated with ir_axioms: Nice to see axiomatic IR gaining momentum.

Come join us at the poster session at ICTIR 2025 to discuss:.- Axioms for Retrieval-Augmented Generation - Learning Effective Representations for Retrieval Using Self-Distillation with Adaptive Relevance Margins

Thrilled to announce that @MattiWiegmann has successfully defended his PhD! 🎉🧑‍🎓 Huge congratulations on this incredible achievement!.#PhDDefense #AcademicMilestone

Congrats to the authors @LukasGienapp, .Tim Hagen, @maik_froebe, @matthias_hagen .@bennostein, @martinpotthast and @hscells .– from @uni_kassel, @Hessian_AI, @Sca_DS, @uni_tue, @UniJena & @bauhaus_uni.

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. 📄

RT @maik_froebe: Do not forget to participate in the #TREC2025 Tip-of-the-Tongue (ToT) Track :). The corpus and baselines (with run files)….

Credit & thanks to the author team @LukasGienapp @DeckersNiklas @martinpotthast @hscells . 📄 Preprint: .💻 Code:

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.

The key idea: we can use the similarity predicted by the encoder itself between positive and negative documents to scale a traditional margin loss. This performs implicit hard negative mining and is hyperparameter-free.

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.

RT @fschlatt1: @maik_froebe @hscells @ShengyaoZhuang @bevan_koopman @guidozuc @bennostein @martinpotthast @matthias_hagen Short: Rank-Dist….

RT @fschlatt1: What an honor to receive both the best short paper award and the best paper honourable mention award at #ECIR2025. Thank you….

RT @ViolaLorella: #ECIR2025 crowd day#2 😍.Cultural #LunchBreak . #Campanile.#sanfrediano.#lucca

🧵 4/4 Credit and thanks to the author team.@LukasGienapp, Tim Hagen, @maik_froebe,.@matthias_hagen, @bennostein, .@martinpotthast, and @hscells .– you can also catch some of them at #ECIR2025 currently if you want to chat about RAG!.

🧵 3/4 This fundamentally challenges previous assumptions about RAG evaluation and system design. But we also show how crowdsourcing offers a viable and scalable alternative! Check out the paper for more. 📝 Preprint @ ️Code/Data is openly available.

🧵2/4 Key findings: 1️⃣ Humans write best? No! LLM responses are rated better than human. 2️⃣ Essay answers? No! Bullet lists are often preferred. 3️⃣ BLEU? No! Reference-based metrics don't align with human preferences. 4️⃣ LLMs as judges? No! Prompted models label inconsistently.

📢 Our paper "The Viability of Crowdsourcing for RAG Evaluation" has been accepted to #SIGIR2025 ! We compared how good humans and LLMs are at writing and judging RAG responses, assembling 1800+ responses across 3 styles, and 47K+ pairwise judgments in 7 quality dimensions. 🧵➡️

RT @tomaarsen: I've just ported the excellent monoELECTRA-{base, large} reranker models from @fschlatt1 & the research network Webis Group….

RT @christopher: 4 million @lichess chess puzzles