5 papers
SynthWorlds: Controlled Parallel Worlds for Disentangling Reasoning and Knowledge in Language Models
Ken Gu, Advait Bhat, Mike A Merrill +4
Evaluating the reasoning ability of language models (LMs) is complicated by their extensive parametric world knowledge, where benchmark performance often reflects factual recall ra…
Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences
Julian Minder, Clément Dumas, Stewart Slocum +4
Finetuning on narrow domains has become an essential tool to adapt Large Language Models (LLMs) to specific tasks and to create models with known unusual properties that are useful…
Valid Survey Simulations with Limited Human Data: The Roles of Prompting, Fine-Tuning, and Rectification
Stefan Krsteski, Giuseppe Russo, Serina Chang +2
Surveys provide valuable insights into public opinion and behavior, but their execution is costly and slow. Large language models (LLMs) have been proposed as a scalable, low-cost…
Ensemble learning of pathology foundation models for precision oncology
Xiangde Luo, Xiyue Wang, Feyisope Eweje +24
Histopathology is essential for cancer diagnosis and treatment selection, and pathology foundation models learn visual representations from whole-slide images (WSIs). However, exis…
Quotegraph: A Social Network Extracted from Millions of News Quotations
Marko Äuljak, Robert West, Andreas Spitz +1
We introduce Quotegraph, a novel large-scale social network derived from speaker-attributed quotations in English news articles published between 2008 and 2020. Quotegraph consists…