🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Very happy to share that our work "Dense Retrieval with Continuous Explicit Feedback for Systematic Review Screening Prioritisation" w/ Shengyao Zhuang, Bevan Koopman, Guido Zuccon has been accepted at SIGIR 2025 #SIGIR2024 as a short paper. Excited for my first #SIGIR experience!

Why you shouldn’t ask ChatGPT for medical advice smh.com.au/national/why-y…

A world-first study has found that when asked a health-related question, the more evidence given to ChatGPT, the less reliable it becomes. Scientists from CSIRO and UQ News found the accuracy of its responses were reduced to as low as 28 per cent. csiro.au/en/news/All/Ne…

Some recent press about our #EMNLP2023 paper on evaluating ChatGPT behaviour on health questions, with Guido Zuccon AEHRC UQ School of EECS

PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval Prompts LLMs to generate hybrid text representations for retrieval without any additional training. 📝arxiv.org/abs/2404.18424 👨🏽‍💻github.com/ielab/PromptRe…

Our paper "PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval" with Xueguang Ma Bevan Koopman Jimmy Lin and Guido Zuccon is now available on arXiv: arxiv.org/abs/2404.18424

We have a PhD scholarship and 2 postdoc openings in the ielab team to work on Information Retrieval and LLMs. Come and join us! 🧵

Great talk by Shengyao Zhuang from CSIRO AEHRC now presenting "Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models" with Guido Zuccon from UQ News and Google Research at #SIGIR2024.

Shengyao Zhuang is now presenting @ ‘Leveraging LLMs for Unsupervised Dense Retriever Ranking’ at SIGIR 2025 Check the paper arxiv.org/abs/2402.04853 to see how to select the dense retriever for your task without training corpora and test labels!

Lots of mentions of work from UQ UQ School of EECS ielab CSIRO AEHRC (Shengyao Zhuang Joel Mackenzie Guido Zuccon) in the talk by Benjamin Piwowarski at the #SIGIR2024 LLM Day ❤️ thanks Benjamin Piwowarski for the shout out, and the great insights in the talk❤️

10 years since that day abc.net.au/news/2024-07-1…

Evaluating generative retrieval systems that directly return generated texts with references is an interesting research problem for the coming years. Now we have Niklas Deckers at #SIGIR2024 presenting perspectives on "Evaluating Generative Ad Hoc IR". webis.de/publications.h…

15. The world in 250 mil. years from now

Our paper "Understanding and Mitigating the Threat of Vec2Text to Dense Retrieval Systems" has been accepted at #sigirap2024! Preprint is available: arxiv.org/pdf/2402.12784 Code: github.com/ielab/vec2text…

Starbucks: Improved Training for 2D Matryoshka Embeddings Improves 2D Matryoshka by using targeted layer-dimension pairs, achieving effectiveness comparable to separately trained models while maintaining adaptability. 📝arxiv.org/abs/2410.13230 👨🏽‍💻github.com/ielab/Starbucks

Share our paper "ReSLLM: Large Language Models are Strong Resource Selectors for Federated Search" with Shengyao Zhuang , Bevan Koopman and Guido Zuccon has been accepted to TheWebConference 2025 as a short. Preprint: arxiv.org/abs/2401.17645 Github: github.com/ielab/SLAT-RsL…

Beware! Document screenshot retrievers are very vulnerable to pixel poisoning attacks! We show it’s possible to generate a single document that will be retrieved at position 1 for all targetted queries. In many cases the user might not even recognise it’s a manipulated document!

🎉 Excited to share the list of our ielab papers accepted at #SIGIR2025 ACM SIGIR! Topics include efficiency in IR, domain-specific IR (SysRev, podcast), screenshot retrievers, hallucination detection, and more. See you in Padua 🇮🇹! Details coming soon, stay tuned!

What an honor to receive both the best short paper award and the best paper honourable mention award at #ECIR2025. Thank you to all the co-authors Maik Fröbe Harry Scells Shengyao Zhuang Bevan Koopman Guido Zuccon Benno Stein Martin Potthast Matthias Hagen 🥳

Maik Fröbe Harry Scells Shengyao Zhuang Bevan Koopman Guido Zuccon Benno Stein Martin Potthast Matthias Hagen Short: Rank-DistiLLM: Closing the Effectiveness Gap Between Cross-Encoders and LLMs for Passage Re-ranking webis.de/publications.h… Full: Set-Encoder: Permutation-Invariant Inter-Passage Attention for Listwise Passage Re-Ranking with Cross-Encoders webis.de/publications.h…