Alexander Hoyle

@miserlis_

Postdoctoral fellow with @ETH_AI_Center. CSS + NLP. Previously CS PhD @umdcs, intern at @msftresearch and @ai2_allennlp.

alexanderhoyle.com

Joined May 2011

614 Following

1,310 Followers

Replies Reposts Media

Alexander Hoyle
@miserlis_
Oct 24
I'll be at #EMNLP2026 --- looking forward to (re)-connecting with folks! Ben will be presenting our work on the automated reproduction of social science results (poster Tuesday at 9:00)
Elliott Ash
@ellliottt
Apr 24
Can AI agents read a social science paper and write the code from scratch to reproduce its results? No access to original code. Just text + data. New paper with Ben Kohler, @david_rzs, @__jae_1, and @miserlis_ 👇
1
Alexander Hoyle
@miserlis_
Sep 4
I really enjoyed working on this paper and learned a lot about reasoning models in the process! Hope the paper will provide equally edifying for readers :)
Kevin Du
@kevdududu
Sep 4
Chain-of-thought often looks meaningful. But are reasoning steps that seem important *actually* important? Our COLM 2026 paper - “Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain-Of-Thought Reasoning” suggests: NOT necessarily ❌ 🧵
Alexander Hoyle
@miserlis_
Aug 25
Now accepted to #EMNLP2026!
Elliott Ash
@ellliottt
Apr 24
Can AI agents read a social science paper and write the code from scratch to reproduce its results? No access to original code. Just text + data. New paper with Ben Kohler, @david_rzs, @__jae_1, and @miserlis_ 👇
1
Alexander Hoyle
@miserlis_
May 27
Delighted to announce the next step in my career! After my postdoc, I will begin a joint appointment at TU Wien and the Complexity Science Hub Vienna as an Assistant Professor in NLP! My deepest thanks to all who helped me along the way I'm hiring—details on PhD positions below
44
Alexander Hoyle
@miserlis_
Apr 27
New preprint out! Recent work tasks LLM agents with re-running existing social science replication code. Given current capabilities, that should be table stakes Here, we move up a level of abstraction, and ask models to reproduce results from a paper’s descriptions alone
Elliott Ash
@ellliottt
Apr 24
Can AI agents read a social science paper and write the code from scratch to reproduce its results? No access to original code. Just text + data. New paper with Ben Kohler, @david_rzs, @__jae_1, and @miserlis_ 👇
1

Alexander Hoyle

Alexander Hoyle’s posts