Giovanni De Toni

A bit late to the party, but @pfrazee, you might want to check out our latest paper (dl.acm.org/doi/full/10.... (RecSys '25, 🏆 Best Paper). We introduce a simple post-hoc way to mitigate unwanted recs (provably) from user feedback (e.g., "Show Less"), making sure the model respects negative signals!

Humbled and honored to announce that this paper won the Best Paper Award at #RecSys2025. Check it out in the proceedings:
dl.acm.org/doi/full/10....

Thanks to my amazing co-authors @giovannidetoni.bsky.social, @erasmopurif.bsky.social, Emilia Gomez, Bruno Lepri and @andreapasserini.bsky.social.

A big shout-out to my collaborators! @erasmopurif.bsky.social, Emilia Gomez, Bruno Lepri, @andreapasserini.bsky.social and @cristiancantoro.bsky.social.

However, instead of just removing unwanted items (which we show can hurt engagement), we provide a data-driven property to pick and show previously seen items, preserving both safety and relevance!

We exploit conformal risk control techniques to find a threshold to decide which items we need to remove from the user feed. The calibration procedure requires simple binary user feedback (e.g., "Like"/"Dislike"), thus linking directly the user preferences to RecSys behaviour.

We propose a model-agnostic, distribution-free method that uses limited binary human feedback to limit exposure to unwanted content in recommender systems, provably, and not just by filtering, but by replacing "risky" items with items the user has already liked!

You Don't Bring Me Flowers: Mitigating Unwanted Recommendations Through Conformal Risk Control Recommenders are significantly shaping online information consumption. While effective at personalizing content, these systems increasingly face criticism for propagating irrelevant, unwanted, and eve...

🎯 Still clicking “Not Interested” but getting the same junk recommendations? You’re not alone!
In our new ACM RecSys'25 paper, we’re tackling the growing problem of unwanted and sometimes harmful content in recommender systems 👉 arxiv.org/abs/2507.16829

@recsys.bsky.social

Are conformal prediction sets always optimal for helping humans solve classification tasks? Not always! In our #NeurIPS paper, we show how finding optimal sets is Np-hard, and we offer a (greedy) solution!
📜arxiv.org/pdf/2405.17544
🪧Join us on Wed 11 (11-2 PM, East Exh. Hall)!