Philip Resnik

To be presented at ACL 2025: Large Language Models Are Biased Because They Are Large Language Models. Article: doi.org/10.1162/coli_a… Short (8min) video: youtube.com/watch?v=WLSuhe… #ACL2025NLP #NLProc #LLMs

Also joint work with @psresnik and @boydgraber. This work concludes a "trilogy" of topic model evaluation papers paper 1: dl.acm.org/doi/10.5555/35… thread 1: x.com/miserlis_/stat… paper 2: aclanthology.org/2022.findings-… thread 2: x.com/miserlis_/stat…

Researchers @UofMaryland are examining how and why some misleading narratives proliferate via strategic use of certain mainstream news articles. The paper—coauthored by Pranav Goel, @_Jon_Green, @davidlazer & @psresnik—was published @NatureHumBehav. nature.com/articles/s4156…

Looking for guidance on raising successful kids in a complicated world? Rebecca Resnik's new podcast is (objectively, even if I'm personally biased!) a great place to go. podcasts.apple.com/us/podcast/cul…

About to do the Vanishing Gradients podcast to talk about LLMs and prompting! x.com/hugobowne/stat…

Just out on arXiv: my paper arguing that harmful biases are an inherent consequence of the underlying assumptions in any large language model, as LLMs are currently formulated. To the extent this is true, those assumptions badly need to be revisited. arxiv.org/abs/2406.13138

I am beyond thrilled to report that my first PhD grad, Mona Diab, has been named a new Fellow of the Association for Computational Linguistics, along with four other terrific scholars. Congratulations to @MonaDiab77!

Honored my paper with @psresnik was accepted to Findings of #EMNLP2023! Many psycholinguistics studies use LLMs to estimate the probability of words in context. But LLMs process statistically derived subword tokens, while human processing does not. Does the disconnect matter? 🧵

📢CLPsych Shared Task '24 🗓️Registration deadline: December 10th ℹ️If you are interested in working with LLMs for "explaining stuff" or in #NLProc for mental health, check out the @CLPsychOrg page! clpsych.org/shared-task-20… Team:@AtzilDana @jennycwchim @i_t_s_dimitris @xrysoflhs

I'm excited to be among the co-authors for this new article, which provides a tutorial introduction to the Eelbrain toolkit. Eelbrain is a *great* bridge for computational linguists interested in neuroscience. elifesciences.org/articles/85012

Great work led by @umdclip undergrad Sander Schulhoff, plus the video overview is fun.

A valuable read for anyone interested in @CLPsych (and more broadly anyone interested in LLMs' connection with psychology and mental health). doi.org/10.1038/s44159… Hats off to @ddemszky and colleagues.

CLPsych 2024 is collocated with EACL and the first CFP is out. We are looking forward to seeing your submissions clpsych.org

Our new publication looks at how PAC donations connect to what gets talked about in the House of Representatives. Expect more great stuff from @Pranav__Goel's recently completed dissertation using NLP methods to better understand American politics. tinyurl.com/59en9333

We are proposing an ACL SIG-CLPsych special interest group for computational linguistics and clinical psychology. If interested please sign up saying you'd like to be a member if the group is approved -- no cost or obligations: forms.gle/aajsUvNRsGzhFq…. (And please share!)

Once again United Healthcare attempts to terminate rehab services for my post-stroke 89yo dad (now while he has COVID, no less!), and once again 3rd-party medical review supports our appeal. @AskUHC @UHC, perhaps there's a message here for you?

Hey @UHC @AskUHC, my 89yo dad is spending Father's Day in the hospital even though he's cleared for discharge because you're throwing clearly needless obstacles in the way of authorizing his rehab. Your appalling Managed Medicare reputation is well deserved.

The Outstanding Study Design Award for ICWSM 2023 goes to: "Mainstream News Articles Co-Shared with Fake News Buttress Misinformation Narratives" by @Pranav__Goel @davidlazer @psresnik