Catherine Chen

CS PhD Candidate @BrownCSDept @health_nlp | Explainability, IR, NLP | ex-SWE at FreeWheel (she/her)

[Catherine Chen @catherineschen]

Full schedule and details can be found on our website: https://t.co/RIH9rFoJUW

[Catherine Chen @catherineschen]

#SIGIR2026 is coming to a close 🥲 but keep the fun going by joining our Second Workshop on Explainability in IR tomorrow! We have a really exciting keynote lined up and an engaging program to discuss how to shape the future of XIR. Hope to see you there!

[Catherine Chen @catherineschen]

I’m in Melbourne for SIGIR! Looking forward to drinking lots of good coffee and doing some sightseeing before the conference gets underway next week ☕️🇦🇺🐨🐧 if you’re around, let’s catch up!

[Catherine Chen @catherineschen]

📣 Call for extended abstract submissions for the 2nd Workshop on Explainability in IR @ SIGIR 2026 in Melbourne, Australia 🇦🇺

Come join us for an exciting day of discussions and writing as we work to create a roadmap for future research!

More info: https://t.co/1ItdWB1IXQ

[Catherine Chen @catherineschen]

I’m in Italy for SIGIR! 🇮🇹 If you’re interested in explainability/interpretability, come by our poster this afternoon (Towards Best Practices of Axiomatic Activation Patching in IR), or our workshop on Explainability in IR on Thursday, would love to chat!

[Catherine Chen @catherineschen]

Last call for extended abstract submissions to our workshop on explainable IR! Join us in Italy this summer for some interesting discussions and tasty food :)

[Maria Heuß @maria_heuss]

📢 DEADLINE EXTENDED by 1 week! Submit your extended abstract on explainable IR - share your published work, ongoing research, or perspectives on the field until April 23rd. #IR #XAI #XIR #SIGIR2025

[Michal Golovanevsky @MichalGolov]

If SOTA models fail to recognize simple shapes, should we be evaluating them on complex geometric tasks? Most MLLMs struggle with counting the number of sides of regular polygons and all MLLMs receive 0% on novel shapes. @WilliamRudmanjr
@_amirbar @vedantpalit1008 [1/6]

[Catherine Chen @catherineschen]

Join us to share your work, connect with other researchers, and discuss the future of explainable IR. We invite submissions for extended abstracts of (1) published work, (2) ongoing research, and (3) completed but unpublished work. Hope to see you in Italy! 🇮🇹

[Catherine Chen @catherineschen]

Interested in explainability, information retrieval, and Italian food??? 🔎 💾 🍝 Submit to our #SIGIR2025 workshop on explainable IR, held this summer in Padova, Italy! Details and website with CfP below 👇

[Maria Heuß @maria_heuss]

Call for Extended Abstracts!

The first edition of the Workshop on Explainable Information Retrieval (WExIR) will be held at SIGIR 2025 in Padova, Italy.

Find all the details on our website: https://t.co/gKCoIa9lXH

We look forward to your submissions. Deadline is April 16th.

[Apoorv Khandelwal @apoorvkh]

Wondering how long it takes to train a 1B-param LM from scratch on your GPUs? 🧵

See our paper to learn about the current state of academic compute and how to efficiently train models! Use our code to test your own models/GPUs!

https://t.co/hvrjwlApN8
https://t.co/1JnEe2CCLr

[Aaron Mueller @amuuueller]

I'm recruiting PhD students for our new lab, coming to Boston University in Fall 2025!

Our lab aims to understand, improve, and precisely control how language is learned and used in natural language systems (such as language models).

Details below!

[Jack McKechnie @JackMcK1999]

At 15:00 on 30 Sept, Catherine Chen @catherineschen from Brown University will give a talk entitled "Advancing Explainable Information Retrieval: Methods for Human-Centered Evaluation and Interpreting Neural IR Models". Details at: https://t.co/stGw3FyQL6

@GlasgowCS
@ir_glasgow

[Catherine Chen @catherineschen]

@ruochenz_ Haha looks that way!

[Catherine Chen @catherineschen]

That’s a wrap on #sigir2024! A little (read: very) nerve wracking to be presenting for the first time, but very grateful for all the interesting discussions that followed! Now all that’s left is to see if I’ll ever make it back to PVD…

[Catherine Chen @catherineschen]

@ShirKi @SIGIRConf Great to meet you at SIGIR! Could @amilah_dul and I be added to the list? Thanks!

[Catherine Chen @catherineschen]

I’m presenting our explainability papers today!👇First stop by at 10:30 during T1.1 (Senate) to learn about our user-centric explainability metric, and then at 1:30 during T2.3 (South American B) for our perspective on new directions for XIR research!

[Health NLP @health_nlp]

More news on #SIGIR2024: @catherineschen presents two papers today!
1. "Evaluating Search System Explainability with Psychometrics and Crowdsourcing"
2. "Axiomatic Causal Interventions for Reverse Engineering Relevance Computation in Neural Retrieval Models" w/ @jack_merullo_

[Catherine Chen @catherineschen]

I’ll be presenting our Perspectives Paper on causal interventions for reverse engineering relevance, and our full paper introducing an evaluation metric for search system explainability (both on Tues!)

[Catherine Chen @catherineschen]

I’m in DC for #SIGIR2024! 🦅 excited to reconnect with old friends and make new ones! Happy to chat about interpretability/explainability and food/drink recommendations I’ve crowdsourced from friends who’ve lived in the area 😎

[William Rudman @WilliamRudmanjr]

Mechanistic interpretability has advanced our understanding of LLMs, but what about multimodal models? Introducing NOTICE. NOTICE is a mech interp pipeline for multimodal models that performs activation patching without relying on Gaussian noise for corruption [1/5]. @MichalGolov

[Catherine Chen @catherineschen]

@SerenaLBooth @BrownUniversity @BrownCSDept Ah yes, thanks for the correction, I got too excited!