Oleg Zendel

ADM+S team wins global LiveRAG Challenge at SIGIR 2025 - ADM+S Centre Researchers from ADM+S at RMIT University have taken out first place in the LiveRAG Challenge at SIGIR 2025, showcasing world-class innovation in Retrieval-Augmented Generation (RAG) technologies.

A team from the ADM+S at RMIT University has taken out first place amongst 70 teams across 27 countries in the LiveRAG Challenge at SIGIR 2025, showcasing world-class innovation in Retrieval-Augmented Generation (RAG) technologies admscentre.org/3IBFe8Z

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

Kun Ran, Shuoqi Sun, Khoi Nguyen Dinh Anh, Damiano Spina, Oleg Zendel
RMIT-ADM+S at the SIGIR 2025 LiveRAG Challenge
https://arxiv.org/abs/2506.14516

Excited to share that my amazing RMIT ADM+S team – @damianospina.com, Kun Ran, @shuoqisun.bsky.social, and Dinh Anh Khoi Nguyen – are global finalists in the #SIGIR #LiveRAG Challenge! I'm incredibly proud of everyone and what we've achieved. What a fantastic journey! 🎉

That's an interesting claim.
My personal experience is actually opposite of this, I noticed that with at least with some LLM based writing tools (including Grammarly) ; are quite common

My first media interview, a great experience!

I really enjoyed the conversation with @jtrippas.bsky.social from @rmitcomputing.bsky.social and Ellen Phiddian from @abcnewsbot.bsky.social.

Thanks for the thoughtful discussion and the opportunity to share insights!

Is Google search getting worse? Maybe what we want from it has changed Has the simple search become less useful in a world of low-information, SEO-optimised sites, and often faulty AI summaries? Are there better ways to navigate the web?

Are search engines getting worse—or is it time to rethink how we search? ADM+S researchers Oleg Zendel, Ashwin Nagappa & Johanne Trippas share insights on search quality, AI & what it means for how we find trustworthy information online @olegzendel.bsky.social @ashwinnag.bsky.social bit.ly/3F8sx44

https://dl.acm.org/doi/proceedings/10.1145/3698204

Proceedings of the 2025 ACM SIGIR Conference on Human Information Interaction and Retrieval #CHIIR2025 are now available at the ACM DL: dl.acm.org/doi/proceedi...

Hackers have hit major super funds. A cyber expert explains how to stop it happening again

Super funds may be missing a basic safeguard to protect retirement savings.

IRRJ, the Information Retrieval Research Journal, is the new player in the information retrieval publication landscape. The first issue has recently been published. Have a look at irrj.org/index, and don't forget to follow @IRRJ.sigmoid.social.ap.brid.gy!

Fantastic keynote by Kathy Brennan at #CHIIR2025! Insightful points on UI design at Google moving beyond the 'average user' to truly personalize experiences. Thought-provoking and inspiring

What makes a good search engine? These 4 models can help you use search in the age of AI To make sure search engines serve us well, it’s helpful to imagine these tools having different roles – whether it’s a “librarian” or a “teacher”.

Our @theconversation.com article discussing 4 ethical models of search engines is out!

theconversation.com/what-makes-a...

@admscentre.org.au
@rmitcomputing.bsky.social
@umbrellacorpn.bsky.social

@rankun203.bsky.social is presenting his Master's work at #CHIIR2025 in Melbourne.

Exploring LLMs to improve query reformulation, showing promising results especially for poor queries. Contrary to prior studies of PRF query expansion, which works mostly for effective queries.

Questions time 😄

There's something quasi-religious about the way some critics of AI declare their total abstinence from it, like a badge of moral purity. You can bet many of the same voices drive cars, eat factory-farmed meat, and otherwise engage with systems that have deep ethical and environmental costs.

Black text on white background. Screenshot from ARC’s Grants Calendar webpage showing which schemes will go ahead next year (upper bullet points), and which will be “paused” pending the outcomes of the review of the National Competitive Grants Program (lower bullet points). Source: https://www.arc.gov.au/funding-research/ARC_grants-calendar

ARC has “paused” future rounds of grant schemes pending outcomes of its NCGP Policy Review.

All schemes previously scheduled to open before 1 July this year will go ahead.

But next year’s Laureates, Industry Fellowships & Discovery Indigenous won’t.

See table👇 & www.arc.gov.au/funding-rese...

Excerpt from the article. Black text on white background with a few links in blue text. Excerpt as follows: “Under the ARC board’s proposals, most stand-alone fellowships would be replaced by “embedded fellowships” funded through other grant schemes and capped at two years. “Traditional four-year fellowships concentrate a significant amount of funds on a small number of individual researchers,” a discussion paper explains. Observers fear this could inadvertently deny many ECRs a toehold in academia because current fellowship schemes such as the Discovery Early Career Researcher Award (Decra) and the mid-career Future Fellowships are available to researchers without positions at universities. This could change under the proposals. The discussion paper implies that recipients of embedded fellowships must already be in “the university workforce” – suggesting that ECRs must obtain employment in the sector before gaining eligibility for ARC grants. That is an “unrealistic” expectation, according to Sharath Sriram, president of Science and Technology Australia. “The assumption is all those who apply are already…in academic roles. That might have been true in the 1990s. It’s not the case anymore. “There’s no stability of employment for people until they are six, seven years out of their PhDs. Universities often use success in grants and fellowships to determine who to employ.” A researcher who monitors grant schemes, using the social media handle “ARC Tracker”, was unconvinced that the proposals would improve opportunities for ECRs. They said changes to fellowship schemes needed to avoid closing “pathways” for young researchers and leaving them “overshadowed by the established group leaders”. ARC Board chair Peter Shergold acknowledged the fellowship changes as one of the “stings in the tail” of his proposals, but said a primary goal of his reforms was “contributing to the development of the next generation of researchers”.

Here’s a report by John Ross in @timeshighered.bsky.social on ARC Board’s proposal to change grant schemes ▶️

www.timeshighereducation.com/news/arc-gra...
[Free login required]

Both @scienceau.bsky.social's & I am worried about opportunities & unintended consequences for early-career researchers👇

An interesting 🧵 worth having a look at

Soaking up (possibly) the last bit of summer this weekend - while wrapping up my reviews!

Screenshot from the ARC Board’s Discussion Paper on the Policy Review of the National Competitive Grants Program (page 33) listing the questions the standard submission form asks you to address. Black text on white background with a heading “Having your say” on dark blue background at the top.

ALL RESEARCHERS

❗️Speak up❗️ if you have opinions, critique or ideas on proposed changes to Australian Research Council grants.

Discuss & distill ideas, sure, but to be considered you MUST make a submission ▶️ submit.dese.gov.au/jfe/form/SV_...

It’s EASY!

Answer these questions in the form👇

Captain it's Wednesday

Captain it's Wednesday

Table from page 25 of the proposed restructure of ARC grants. Back text on white background, with the table delineated by a dark blue header row and alternating light and very light blue rows.

The ARC Board has proposed a major shake-up of the National Competitive Grants Program ▶️ www.arc.gov.au/engage-us/co...

I've only skimmed so far, but they propose reducing 13 grant schemes to 6, with intent & scope in the table👇

Submissions are being accepted in response until 13 April. Get to it!

The list of accepted papers, workshops, and tutorials for #CHIIR2025 are now online!

chiir2025.github.io/schedule.html

A bird's-eye view of a former Auschwitz II-Birkenau camp showing a wide dirt pathway flanked by parallel rows of barbed-wire fences. Groups of visitors walk along the path, surrounded by the remnants of brick structures and barracks, now reduced to foundations. Green grass contrasts with the somber history of the site, as the path leads toward a guard tower in the distance.

Auschwitz was at the end of a long process. It did not start from gas chambers.

This hatred was gradually developed by humans. From ideas, words, stereotypes & prejudice through legal exclusion, dehumanization & escalating violence... to systematic and industrial murder.

Auschwitz took time.

That didn't take long! Nomic AI has finetuned the new ModernBERT-base encoder model into a strong embedding model for search, classification, clustering and more!

Details in 🧵

Adapting Generative Information Retrieval Systems to Users, Tasks, and Scenarios Generative Information Retrieval (GenIR) signifies an advancement in Information Retrieval (IR). GenIR encourages more sophisticated, conversational responses to search queries by integrating generati...

Hohoho! 🎅🏼🎄
Our book chapter “Adapting Generative Information Retrieval Systems to Users, Tasks, and Scenarios” is now online!

w/ @jtrippas.bsky.social @umbrellacorpn.bsky.social

@rmitcomputing.bsky.social
@admscentre.org.au

#GenIR #GenAI

link.springer.com/chapter/10.1...

Adapting Generative Information Retrieval Systems to Users, Tasks, and Scenarios Generative Information Retrieval (GenIR) signifies an advancement in Information Retrieval (IR). GenIR encourages more sophisticated, conversational responses to search queries by integrating generati...

New year, new insights! 🎉

Our book chapter "Adapting Generative Information Retrieval Systems to Users, Tasks, and Scenarios" is now online! w/ @jtrippas.bsky.social @damianospina.com @umbrellacorpn.bsky.social

@rmitcomputing.bsky.social #GenIR
#GenAI #SIGIR

link.springer.com/chapter/10.1...

We invite PhD students to submit your work and join us at PhD Symposium @TheWebConf 2025, (www2025.thewebconf.org/phd-symposium). The submission due date is 18 Dec, 2024 (AOE)! We will see you in the beautiful and amazing Sydney down under! #WWW2025 #WebConf2025

ADM+S project funded $6 million to measure First Nations digital inclusion Funding of $6 million will support a new three-year project led by ADM+S to collect data on the digital inclusion experiences of First Nations people in urban, regional and remote areas across Austral...

ADM+S has been awarded $6 million in funding for a new three-year project to collect data on the digital inclusion experiences of First Nations people in urban, regional and remote areas across Australia @Telstra #DigitalInclusion bit.ly/3VDzUFF

Improvised social mixer after a long Day 2! #sigirap2024 #naarm @olegzendel.bsky.social
@admscentre.org.au