Who's Who of AI

Julia Mendelsohn

444 trust researcher @jmendelsohn2.bsky.social · 4,246 followers
NLP & language AI research
Why they matter

Researcher with public evidence across NLP & language, AI research.

AI signals
2
past 30d
Sources
2
distinct domains
Discussões
0
past 30d
Latest signal
19d ago
View every signal from Julia Mendelsohn →
Asst Prof @UMD Info College. NLP, computational social science, political communication, linguistics. Past: Data Science Postdoc @UChicago, Info PhD @UMich, CS + Lx @Stanford. Interests: cats, Yiddish, talking to my cats in Yiddish.
What they're sharing

Articles & links

↻ Julia Mendelsohn reposted
Dustin Wright @dustinbwright.com

Which, whose, and how much knowledge do LLMs represent? I'm excited to share our preprint answering these questions: "Epistemic Diversity and Knowledge Collapse in Large Language Models" 📄Paper: arxiv.org/pdf/2510.04226 💻Code: github.com/dwright37/ll... 1/10

arxiv.org View on Bluesky →
↻ Julia Mendelsohn reposted
Dustin Wright @dustinbwright.com

Which, whose, and how much knowledge do LLMs represent? I'm excited to share our preprint answering these questions: "Epistemic Diversity and Knowledge Collapse in Large Language Models" 📄Paper: arxiv.org/pdf/2510.04226 💻Code: github.com/dwright37/ll... 1/10

GitHub - dwright37/llm-knowledge: A package for extracting knowledge and measuring epistemic diversity in LLMs. Associated with the paper "Epistemic Diversity and Knowledge Collapse in Large Language Models" github.com
AI Weekly's analysis →
  • A study of 27 LLMs across 155 topics and 12 countries found every system was less epistemically diverse than a basic web search baseline.
  • Larger models were counterintuitively less diverse than smaller ones, while retrieval-augmented generation improved diversity across the systems tested.
  • For country-specific topics, LLM parametric knowledge systematically reflected English sources over local-language ones, the authors report.
Read full analysis →
 View on Bluesky →

Just arrived in Burlington for #IC2S2! My student Krystal Gong will be presenting: 👉 Thursday @ 10:45 in Chittenden (413) about geopolitical stance formation in LLMs 👉 Friday @ 14:15 in Jost Foundation (422) about quantifying persuasive cues in text (arxiv.org/abs/2606.14580) …

Persuasion Index: A Theory-Guided Framework for Persuasion Analysis arxiv.org
AI Weekly's analysis →
  • Persuasion Index is a taxonomy of 15 dimensions grounded in psychology and communication, implemented with 55 sub-features from lexicons and rule-based detectors.
  • The authors evaluate PI on four public datasets varying in domain, style, and outcome measures, and report linear models carry meaningful predictive signal while staying lightweight.
  • PI is released as an open-source package and web interface for principled and auditable analysis of human and AI-mediated communication.
Read full analysis →
View on Bluesky · ♥ 11 ↻ 1 ↩ 0 · 2 from the directory shared this · 56d ago
Their network

In Julia Mendelsohn's orbit

Center = Julia Mendelsohn. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.

Are you Julia Mendelsohn? Show it.

Add the Who’s Who of AI badge to your site or bio. It links back to this profile.

Listed in AI Weekly's Who's Who of AI

Markdown: [![Listed in AI Weekly's Who's Who of AI](https://aiweekly.co/modules/custom/aiweekly_whoswho/images/whoswho-badge.svg)](https://aiweekly.co/whos-who/person/jmendelsohn2-bsky-social)