iiinova — where your digital self keeps evolving

Arnav Arora

@rnv.bsky.social

2.8K followers 1.1K following 33 posts

CS PhD student, University of Copenhagen | LLM cultural value alignment, safety, political communication, AI ethics | he/him. scholar.google.com/citations?user=E…

Posts Replies Media

Arnav Arora @rnv.bsky.social · 25/04/2025

Happy to share that I've joined the Apple Machine Learning Research team in Copenhagen as a research intern! Will continue to build on topics from my PhD, equitably advancing LLM access for all, working with @maartjeterhoeve.bsky.social and Natalie Schluter.

3290

Arnav Arora @rnv.bsky.social · 07/04/2025

Using our method, you can also get issue-specific frames inductively from the article texts. When publishers are compared across the political spectrum, some clear patterns of how the left frames Immigration vs the right.

110

Arnav Arora @rnv.bsky.social · 07/04/2025

Across topics, we find substantial differences in framing across the article and the image. These hold across political leanings as well.

110

Arnav Arora @rnv.bsky.social · 07/04/2025

We collect a dataset of 500k articles and images from various publishers in the US, across the political spectrum and systematically analyse differences in framing across them.

120

Arnav Arora @rnv.bsky.social · 07/04/2025

🚨New pre-print 🚨 News articles often convey different things in text vs. image. Recent work in computational framing analysis has analysed the article text but the corresponding images in those articles have been overlooked. We propose multi-modal framing analysis of news: arxiv.org/abs/2503.20960

13710

Arnav Arora @rnv.bsky.social · 13/11/2024

2/2 keynotes at #EMNLP2024 so far have brought up the dual use nature of LLMs. Good time to resurface our work on surveying LLM practitioners on this imp topic & bringing potential mitigations to light. aclanthology.org/2023.finding...

070