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
(6/9) We put a suite of aligned models, and their instruction fine-tuned counterparts, to the test and found:
* no model reaches human-like diversity of thought.
* aligned models show LESS conceptual diversity than instruction fine-tuned counterparts
* no model reaches human-like diversity of thought.
* aligned models show LESS conceptual diversity than instruction fine-tuned counterparts
February 10, 2025 at 5:20 PM
(6/9) We put a suite of aligned models, and their instruction fine-tuned counterparts, to the test and found:
* no model reaches human-like diversity of thought.
* aligned models show LESS conceptual diversity than instruction fine-tuned counterparts
* no model reaches human-like diversity of thought.
* aligned models show LESS conceptual diversity than instruction fine-tuned counterparts
(5/9) Our experiments are inspired by human studies in two domains with rich behavioral data.
February 10, 2025 at 5:20 PM
(5/9) Our experiments are inspired by human studies in two domains with rich behavioral data.
(4/9) We introduce a new way of measuring the conceptual diversity of synthetically-generated LLM "populations" by considering how its “individuals’” variability relates to that of the population.
February 10, 2025 at 5:20 PM
(4/9) We introduce a new way of measuring the conceptual diversity of synthetically-generated LLM "populations" by considering how its “individuals’” variability relates to that of the population.
(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