A list explaining key ML concepts and papers: github.com/dair-ai/ML-Pap… v/elvis

#QUARE23 is kicking off! Looking forward to half day of discussions about Measuring the Quality of Explanations in Recommender Systems QUARE '23, #RecSys2023, ACM RecSys Oana Inel, Milda Norkute, alessandro , Nicolas Mattis

Is it acceptable to sacrifice accuracy for explainability? The real question we should be asking who benefits from that Olfa Nasraoui at #QUARE23, QUARE '23, #RecSys2023, ACM RecSys

What are we trying to achieve with explainability? Evaluation without purpose doesn't make sense. And should trust really be the end goal? @navatintarev #QUARE23, QUARE '23, #RecSys2023, ACM RecSys

Excited to join the expert panel at the QUARE '23 ACM RecSys & discuss how to balance user needs + org objectives in #XAI. Thx for the invitation Milda Norkute! Exciting cross-pollination from #HCXAI workshop at CHI! Props to the organizers for... #QUARE23 #RecSys2023 1/2

How can an explanations boost people’s critical thinking? We should be able the system as needed, not just encourage to trust systems more – @navatintarev #QUARE23, QUARE '23, #RecSys2023, ACM RecSys

All recommender systems are multi-stakeholder says Robin Burke at #QUARE23 There are often key emissions in explanations of recommender systems and calls the industry to change QUARE '23, #RecSys2023, ACM RecSys

Work by Upol Ehsan et al. encourages to think not only about different stakeholder needs but also how their background impacts perception of explanations & how surprising some of the perceptions can be. Thank you for joining & sharing! #QUARE23 QUARE '23 #RecSys2023

A fast-food mentality to deploy ready-made #ML approaches may be what's hampering to move beyond post-hoc rationale generation for #RecSys Upol Ehsan – great discussion in the session session of #QUARE23 ACM RecSys #RecSys2023

Really enjoyed moderating the panel of "Generating explanations: balancing user needs & organisational objectives". Had some great questions & answers on what really drives #explainability, issues & how they be addressed #QUARE23, QUARE '23 #RecSys2023 Upol Ehsan

'Regulation' is so overused as of late, that it risks losing its meaning. I teamed up with regulation global expert @SRanchordas & NLP stars Nikos Aletras Jerry Spanakis 🟥 🦋 gerasimoss.bsky.social Ilias Chalkidis to shed light on the missing parts of the LLM & genAI debate #EMNLP2023 arxiv.org/abs/2310.05553

During times of conflict and suffering, we can only hope that outsiders who are not immediately affected will nurture seeds of peace. The job of intellectuals, artists and scholars is to try and go deeper. To try and see the complexity of reality, especially in today's climate of

Happy to share that AI Assisted Research for legal, on Westlaw Precision I had the chance to work on this year has finally been launched! legal.thomsonreuters.com/blog/legal-res…

Happy to share that our paper "Evaluating Interactive Topic Models in Applied Settings" was accepted as a case study to #CHI2024 🙏🍾. Pre-print will be available once submission is finalised! ACM CHI Conference #workingatTR

Designing UX for generative AI is a new area that comes with its own challenges. Our team just published design principles for generative AI applications that are being used in IBM to craft effective and safe user experiences with GenAI. medium.com/design-ibm/des…

#CHI2024 program is out! Happy to be able to contribute this year. Here is the link to our work in the program of the conference as well as the preprint: lnkd.in/daXHn6v9 lnkd.in/dSirf6ZV