Lightnews — Scholar-powered news

Prof. Nava Tintarev @navatintarev.bsky.social · 8d

“It actually doesn’t take much to be considered a difficult woman. That’s why there are so many of us.” ~ Jane Goodall

Prof. Nava Tintarev @navatintarev.bsky.social · 8d

“You cannot get through a single day without having an impact on the world around you. What you do makes a difference, and you have to decide what kind of difference you want to make." ~ Jane Goodall

Reposted by Prof. Nava Tintarev

Alan Said @alansaid.com · 17d

A preliminary call for papers for #umap2026 is now available on the conference's website. Check it out, mark your calendars, and get to work on those papers. www.um.org/umap2026/cal...
@umapconf.bsky.social (#recsys2025)

Preliminary Call for Papers – ACM UMAP 2026

www.um.org

7 4

Reposted by Prof. Nava Tintarev

Tim Miller @tmiller-uq.bsky.social · 25d

I'm hiring again! Please share. I'm recruiting a postdoc research fellow in human-centred AI for scalable decision support. Join us to investigate how to balance scalability and human control in medical decision support. Closing date: 4 October (AEST).
uqtmiller.github.io/recruitment/

Recruitment

uqtmiller.github.io

1 7 2

Reposted by Prof. Nava Tintarev

taimlab.bsky.social @taimlab.bsky.social · May 27

We have two papers accepted by our PhD students, one at SIGIR 2025: “RecGaze: The First Eye Tracking and User Interaction Dataset for Carousel Interfaces” by Jingwei Kang and one at NAACL 2025: “kNN For Whisper And Its Effect On Bias And Speaker Adaptation” by Maya Nachesa. Please check them out!

1 1

Prof. Nava Tintarev @navatintarev.bsky.social · Sep 10

A new addition for the summer is a placeholder gallery for visual explanation interfaces so visitors can see what these are and just how varied they can be (not yet platform-proofed).
navatintarev.com

Nava Tintarev

Prof. Nava Tintarev

navatintarev.com

2

Prof. Nava Tintarev @navatintarev.bsky.social · Sep 10

Delayed summer announcement: my new website is up and should be more mobile-friendly than its predecessor.

1 2

Prof. Nava Tintarev @navatintarev.bsky.social · Sep 10

Ehud Reiter writes more about this in his blog here: ehudreiter.com/2025/06/25/p...

Pre-print here: arxiv.org/abs/2506.18760

Prof. Nava Tintarev @navatintarev.bsky.social · Sep 10

4) Domain shift: The world has changed since the model was built. This includes societal changes (eg, legalisation of same-sex marriage) and changes in scientific knowledge and interventions.

1

Prof. Nava Tintarev @navatintarev.bsky.social · Sep 10

2)Domain knowledge shows that the feature does not matter: Scientific evidence shows that the feature does not make a sig. difference. 3)Insufficient data: The feature may matter, but the model builders did not have sufficient high-quality training data to reliably model the feature’s impact.

1 1

Prof. Nava Tintarev @navatintarev.bsky.social · Sep 10

She identified four reasons for explaining why a feature is ignored:
1) Data shows the feature does not matter: The feature is ignored because the data shows that the feature has minimal impact on the model’s prediction.

1

Prof. Nava Tintarev @navatintarev.bsky.social · Sep 10

Our joint PhD student Adarsa Sivaprasad is presenting her work at an AI and Healthcare conference: Patient-Centred Explainability in IVF Outcome Prediction. She has been studying what kind of explanations users need from OPIS, which is a tool that predicts the likelihood of success in IVF.

This link will take you to a page that’s not on LinkedIn

lnkd.in

1 1 2

Prof. Nava Tintarev @navatintarev.bsky.social · Sep 10

🔹 Demo Track – Bulat Khaertdinov (with Mirela Carmia Popa) showcasing VisualReF: an Interactive Image Search Prototype with Visual Relevance Feedback 🔍🖼️
🔹 The RecSys Challenge 2025 – Francesco Barile as co-organizer of this year’s challenge! 🔥 More info here: www.recsyschallenge.com/2025/

RecSys Challenge 2025

www.recsyschallenge.com

1

Prof. Nava Tintarev @navatintarev.bsky.social · Sep 10

🔹 Doctoral Consortium – Dina Zilbershtein on Fair and Transparent Recommender Systems for Advertisements 💡
🔹 Short Paper Track – Cedric Waterschoot (with Francesco Barile) asking: “Consistent Explainers or Unreliable Narrators? Understanding LLM-generated Group Recommendations” 🤖📚

RecSys Challenge 2025

www.recsyschallenge.com

1 1

Prof. Nava Tintarev @navatintarev.bsky.social · Sep 10

🚀 To summarize, University of Maastricht and our Explainable Artificial Intelligence theme is heading to ACM RecSys 2025 with a line-up of contributions 🎉
✨ Here’s where you can find us:

1 1 4

Prof. Nava Tintarev @navatintarev.bsky.social · Sep 10

Many thanks to the colleagues who supplied feedback on early drafts and others with who I simply discussed these ideas with less formally! Pre-print here: navatintarev.com/fai_tintarev....

navatintarev.com

1 1

Prof. Nava Tintarev @navatintarev.bsky.social · Sep 10

I conclude by proposing constructive strategies for balancing empirical rigor with practical realities when assessing the quality of explainable AI:
a) systematic reporting of user, task, and context;
b) an investment in reproducibility studies, and
c) more meta-analyses of experiments.

1 2

Prof. Nava Tintarev @navatintarev.bsky.social · Sep 10

If changing the user, task, or context ‘changes’ explanation quality by 10%, it may not be meaningful to report a 2-3% performance improvement that does not control for these variables.

1

Prof. Nava Tintarev @navatintarev.bsky.social · Sep 10

Real-world conditions often shape system performance in ways that (purely) data-driven approaches don’t fully capture. Stronger, I warn that switching from user-centered to offline metric-based evaluation may appear to resolve some issues, but these are latent rather than absent.

1

Prof. Nava Tintarev @navatintarev.bsky.social · Sep 10

Explanations need to be tailored to the user, the task, and the context—whether that’s a domain expert making critical decisions, a layperson under time pressure, or someone seeking to improve a model. Without this alignment, it’s difficult to truly assess explanation quality.

1 1

Prof. Nava Tintarev @navatintarev.bsky.social · Sep 10

In my Frontiers in Artificial Intelligence talk (at ECAI'25) I will present a position piece on XAI evaluation. I will share insights from nearly 20 years of studying how people interact with explanation interfaces. I draw lessons from multiple research communities: NLP, IR, and ML

This link will take you to a page that’s not on LinkedIn

lnkd.in

1 2

Reposted by Prof. Nava Tintarev

ACL @aclmeeting.bsky.social · Jul 30

🕊️ Lifetime Achievement Award at #ACL2025NLP

A standing ovation for Prof. Kathy McKeown, recipient of the ACL 2025 Lifetime Achievement Award! 🌟

2 5 30

Prof. Nava Tintarev @navatintarev.bsky.social · Jul 23

Do you have an alternative to facebook groups? I'd like to keep a community (monthly in person events) running, but do not want to force members to stay on Facebook (or pay or sell data for ads).

1

Reposted by Prof. Nava Tintarev

European Research Council (ERC) @erc.europa.eu · Jul 9

📣 Ever considered applying for a ERC Starting Grant? The 2026 Call for proposals is now open!

Application portal 👉 lnkd.in/dcsPAwqJ
Information for Applicants 👉 lnkd.in/dsE6B8eE

Deadline to apply for #ERCStG is 14 October 2025.

20 30

Prof. Nava Tintarev @navatintarev.bsky.social · Jul 6

But also from other chairs- program chair, workshop chair etc
But you’re right, this protects the organization but may by offenders be too far away compared to more (potential) immediate rewards.