cool work 😍🥳

Chaining LLM calls can improve output quality, but navigating the massive space of task decompositions is challenging. Revisiting the established field of crowdsourcing, we distill strategies for effective LLM chain design and identify opportunities for future research. [1/11]

I am thrilled to join Microsoft Research working with the HAX team at AI Frontiers!

I will be at #chi2024 , and our team is hiring researchers & engineers; this is your chance to shape the future of Human-AI Interaction, so please get in touch!
aka.ms/haxteam

📢We are excited to share the 34 accepted papers for the 1st workshop on Human-centerd Evalulation and Auditing of Language Models.

Cannot wait to bring all the brilliant minds together next week! #CHI2024

See you at HEAL@CHI24!

More: tinyurl.com/3zmvxmu6
#HCI #NLProc

Grimy windshield shot rolling towards the tornado near Lincoln last friday--crazy day

For the 7th time, we’re back! The Workshop on Visualization for AI Explainability ( #visxai ) will accept “explorables” & “explainables” that visualize, explain, and tell interactive stories about AI. #ieeevis

➡️ Deadline: July 30, 2024

visxai.io

📢BREAKING: You can attend the *hybrid* Human-centered Explainable AI ( #HCXAI ) workshop without an accepted paper!

💡Spots are extremely limited so fill this out ASAP: forms.gle/Zc91L1R9AtmqPr…

Why are we opening things up?

💡Over the last 4 years, practitioners & policymakers…

cool work J.D. Zamfirescu Ian Arawjo (@[email protected]) 🥳

love it!!

“Can we get a new text analysis tool?”
“No—we have Topic Model at home”

Topic Model at home: outputs vague keywords; needs constant parameter fiddling🫠

Is there a better way? We introduce LLooM, a concept induction tool to explore text data in terms of interpretable concepts🧵

Please retweet:
My students are recruiting participants for a study on technology to support physical activity. If you are interested in getting more exercise and own an iPhone, please fill out our screening survey: bit.ly/physical-activ…

weeeeeeeeeeeee ❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️

what's up with engineering students?

Meanwhile, according to student feedback, men have a total monopoly on 'cool' and 'funny.'

This shows frequency of the word 'unqualified' in teaching reviews. Women in orange, men in blue.

For an example of how gendered language on teaching evals disadvantages women in academia, let's look at Ben Schmidt's interactive tool that allows you to search teaching reviews by keyword, separated by gender.

Here's the word 'genius.' Men are blue, women are orange.

With another semester ending, here's your annual reminder that teaching evaluations systemically disadvantage women. Even when controlling for grades and other factors, students (esp. males) consistently give female professors lower scores. This can have serious ramifications.🧵

I will be defending my PhD thesis, Training Human-AI Teams, on April 25th at MIT and on Zoom! Please DM me or email for a link! -- (image generated after an hour of prompting DALL·E)