Anjali Kantharuban's Avatar

Anjali Kantharuban

@anjaliruban

PhD in Language Technology @ CMU, working on NLP for Dialects | Formerly @ Cambridge & UC Berkeley

326
Followers
147
Following
2
Posts
11.11.2024
Joined
Posts Following

Latest posts by Anjali Kantharuban @anjaliruban

An overview of the work “Research Borderlands: Analysing Writing Across Research Cultures” by Shaily Bhatt, Tal August, and Maria Antoniak. The overview describes that We  survey and interview interdisciplinary researchers (§3) to develop a framework of writing norms that vary across research cultures (§4) and operationalise them using computational metrics (§5). We then use this evaluation suite for two large-scale quantitative analyses: (a) surfacing variations in writing across 11 communities (§6); (b) evaluating the cultural competence of LLMs when adapting writing from one community to another (§7).

An overview of the work “Research Borderlands: Analysing Writing Across Research Cultures” by Shaily Bhatt, Tal August, and Maria Antoniak. The overview describes that We survey and interview interdisciplinary researchers (§3) to develop a framework of writing norms that vary across research cultures (§4) and operationalise them using computational metrics (§5). We then use this evaluation suite for two large-scale quantitative analyses: (a) surfacing variations in writing across 11 communities (§6); (b) evaluating the cultural competence of LLMs when adapting writing from one community to another (§7).

🖋️ Curious how writing differs across (research) cultures?
🚩 Tired of “cultural” evals that don't consult people?

We engaged with interdisciplinary researchers to identify & measure ✨cultural norms✨in scientific writing, and show that❗LLMs flatten them❗

📜 arxiv.org/abs/2506.00784

[1/11]

09.06.2025 23:29 👍 72 🔁 30 💬 1 📌 5

Assuming this is the true criteria they are using, it’s telling that “female” and “woman” are on this list but “male” and “man” are not 🙃

04.02.2025 16:05 👍 4 🔁 0 💬 2 📌 0

Can I be added too?

21.11.2024 15:23 👍 3 🔁 0 💬 0 📌 0

With @jerelev.bsky.social 's vote and suggestions, here is it:
go.bsky.app/AU2wEvo

Send replies (and pretty plots) to be added :D

21.11.2024 01:44 👍 16 🔁 3 💬 7 📌 0
Screenshot of the paper title "What Goes Into a LM Acceptability Judgment? Rethinking the Impact of Frequency and Length"

Screenshot of the paper title "What Goes Into a LM Acceptability Judgment? Rethinking the Impact of Frequency and Length"

💬 Have you or a loved one compared LM probabilities to human linguistic acceptability judgments? You may be overcompensating for the effect of frequency and length!
🌟 In our new paper, we rethink how we should be controlling for these factors 🧵:

20.11.2024 18:07 👍 84 🔁 19 💬 1 📌 4
This map shows locations for endangered languages in Europe ranked by language vitality

This map shows locations for endangered languages in Europe ranked by language vitality

Always a new linguistic treasure to unearth: I didn't know this UNESCO map from 2018! Of course there is much to say about how accurate it is, with dialects vs languages, extinct vs endangered, but regardless, it shows a type of linguistic diversity in Europe that is rarely highlighted. #LingSky

19.11.2024 07:32 👍 37 🔁 12 💬 5 📌 4

I'm keeping track of people at the CMU Language Technologies Institute here: go.bsky.app/NhTwCVb. Follow along!

12.11.2024 14:54 👍 7 🔁 3 💬 0 📌 0