Sonia Murthy
@soniakmurthy.bsky.social
cs phd student and kempner institute graduate fellow at harvard.
interested in language, cognition, and ai
soniamurthy.com
interested in language, cognition, and ai
soniamurthy.com
Pinned
Sonia Murthy
@soniakmurthy.bsky.social
· Feb 10
(1/9) Excited to share my recent work on "Alignment reduces LM's conceptual diversity" with @tomerullman.bsky.social and @jennhu.bsky.social, to appear at #NAACL2025! 🐟
We want models that match our values...but could this hurt their diversity of thought?
Preprint: arxiv.org/abs/2411.04427
We want models that match our values...but could this hurt their diversity of thought?
Preprint: arxiv.org/abs/2411.04427
Reposted by Sonia Murthy
NEW blog post: Do modern #LLMs capture the conceptual diversity of human populations? #KempnerInstitute researchers find #alignment reduces conceptual diversity of language models. bit.ly/4hNjtiI
Alignment reduces conceptual diversity of language models - Kempner Institute
As large language models (LLMs) have become more sophisticated, there’s been growing interest in using LLM-generated responses in place of human data for tasks such as polling, user studies, and […]
bit.ly
February 10, 2025 at 3:19 PM
NEW blog post: Do modern #LLMs capture the conceptual diversity of human populations? #KempnerInstitute researchers find #alignment reduces conceptual diversity of language models. bit.ly/4hNjtiI
(1/9) Excited to share my recent work on "Alignment reduces LM's conceptual diversity" with @tomerullman.bsky.social and @jennhu.bsky.social, to appear at #NAACL2025! 🐟
We want models that match our values...but could this hurt their diversity of thought?
Preprint: arxiv.org/abs/2411.04427
We want models that match our values...but could this hurt their diversity of thought?
Preprint: arxiv.org/abs/2411.04427
February 10, 2025 at 5:20 PM
(1/9) Excited to share my recent work on "Alignment reduces LM's conceptual diversity" with @tomerullman.bsky.social and @jennhu.bsky.social, to appear at #NAACL2025! 🐟
We want models that match our values...but could this hurt their diversity of thought?
Preprint: arxiv.org/abs/2411.04427
We want models that match our values...but could this hurt their diversity of thought?
Preprint: arxiv.org/abs/2411.04427