Peter Carragher

Yep, I'm on Substack: to make my research accessible and useful, I'll translate my work into digestible posts that explain how I study the local news market at scale, through text mining, to ask questions about media ownership, news deserts, and democracy: shorturl.at/q3VKI

As well as presenting this paper, it was a pleasure getting to talk to so many incredible researchers and learn about recent work in the @nlp4posimpact.bsky.social and online abuse and harms communities.

Last week, I presented my recent paper on memorization and hallucination in LVLMs at @l2m2workshop.bsky.social #ACL2025.

TLDR: model memorization may be more prevalent over image sources vs. text! Details here: aclanthology.org/2025.l2m2-1....

Just wrapped up my first IC2S2 conference with a talk on our ongoing research into how ownership structures of broadcasting companies influences editorial decisions in news outlets.

Check out our News Guessing game at newsguess.petercarragher.com and contribute to our research media ownership!

Excited to share our FAME method for news identification: Fingerprint-to-Article Matching for Events from a DB! We use it to study news coverage of disasters and conflicts (w @brenocon.bsky.social @ethanz.bsky.social). Check out our talk and poster at @icwsm.bsky.social!🧵👇
arxiv.org/abs/2506.12925

Just gave a talk about Dredge Words—queries for which unreliable domains rank highly #icwsm2025

ojs.aaai.org/index.php/IC...

SegSub: Evaluating Robustness to Knowledge Conflicts and Hallucinations in Vision-Language Models (MisD workshop)
workshop-proceedings.icwsm.org/abstract.php...

Mapping the Scientific Literature on Misinformation Interventions: A Bibliometric Review (COMPASS workshop)
workshop-proceedings.icwsm.org/abstract.php...
@kingcatherine.bsky.social

Bridging Social Media and Search Engines: Dredge Words and the Detection of Unreliable Domains
ojs.aaai.org/index.php/IC...
@evanup.bsky.social

Excited to have two workshop papers and one main conference paper that I've been involved in being presented at @icwsm.bsky.social! Thanks @kingcatherine.bsky.social and @evanup.bsky.social for letting me tag along. Details below.

Check out the full paper here, which is upcoming at the ICWSM MisD workshop (see you in Copenhagen!): arxiv.org/pdf/2502.14908

Thanks to my co-authors! @nikitharao.bsky.social @icwsm.bsky.social

Finetuning helps identify counterfactual samples and prevent hallucinations.

Preprint! Vision-language models like GPT-4o fail to identify multimodal knowledge conflicts and frequently hallucinate on counterfactual samples. Try out the batsman example below (promt = "what is he holding?").

How crawlers impact the operations of the Wikimedia projects Since the beginning of 2024, the demand for the content created by the Wikimedia volunteer community – especially for the 144 million images, videos, and other files on Wikimedia Commons – has grow…

Another chapter in AI biting the hand that feeds it: Wikipedia’s bandwidth surged 50% since January thanks to AI crawlers.

Unlike search engines, they send no traffic back so no new users, no new donors. Just rising costs and a shrinking audience.

A raw deal for a cornerstone of the free web.

Misinformation Resilient Search Rankings with Webgraph-Based Interventions | ACM Transactions on Intelligent Systems and Technology The proliferation of unreliable news domains on the internet has had wide-reaching negative impacts on society. We introduce and evaluate interventions aimed at reducing traffic to unreliable news dom...

@evanup.bsky.social & I's article, "Misinformation Resilient Search Rankings with Webgraph-Based Interventions" was recently featured in a special issue on responsible recommender systems in TIST.

Sharing it here instead of on X for... reasons.

dl.acm.org/doi/full/10....

An article covering our most recent paper on Google’s explicit content moderation :)