Arvid Frydenlund
@arvidf.bsky.social
Ph.D student at UofT in machine learning and NLP
First post!
'Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More More'
arxiv.org/abs/2503.10542
A follow-up to my EMNLP paper now on arxiv. A preliminary version of this will also be at the #SCSLWorkshop at #ICLR2025
'Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More More'
arxiv.org/abs/2503.10542
A follow-up to my EMNLP paper now on arxiv. A preliminary version of this will also be at the #SCSLWorkshop at #ICLR2025
Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More More
This work concerns the path-star task, a minimal example of searching over a graph. The graph, $G$, is star-shaped with $D$ arms radiating from a start node, $s$. A language model (LM) is given $G$, $...
arxiv.org
March 14, 2025 at 2:18 PM
First post!
'Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More More'
arxiv.org/abs/2503.10542
A follow-up to my EMNLP paper now on arxiv. A preliminary version of this will also be at the #SCSLWorkshop at #ICLR2025
'Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More More'
arxiv.org/abs/2503.10542
A follow-up to my EMNLP paper now on arxiv. A preliminary version of this will also be at the #SCSLWorkshop at #ICLR2025