Breaking Free Transformer Models: Task-specific Context Attribution Promises Improved Generalizability Without Fine-tuning Pre-trained LLMsby Stepan…
Recovering Mental Representations from Large Language Models with Markov Chain Monte Carloby Jian-Qiao Zhu, Haijiang…
Incoherent Probability Judgments in Large Language Modelsby Jian-Qiao Zhu, Thomas L. GriffithsFirst submitted to arxiv…
Towards Generating Informative Textual Description for Neurons in Language Modelsby Shrayani Mondal, Rishabh Garodia, Arbaaz…
ShaRP: A Novel Feature Importance Framework for Rankingby Venetia Pliatsika, Joao Fonseca, Kateryna Akhynko, Ivan…
A Tournament of Transformation Models: B-Spline-based vs. Mesh-based Multi-Objective Deformable Image Registrationby Georgios Andreadis, Joas I.…
Can Large Language Models be Trusted for Evaluation? Scalable Meta-Evaluation of LLMs as Evaluators via…
Two Heads Are Better Than One: Integrating Knowledge from Knowledge Graphs and Large Language Models…
Scalable Mechanism Design for Multi-Agent Path Findingby Paul Friedrich, Yulun Zhang, Michael Curry, Ludwig Dierks,…
ViTree: Single-path Neural Tree for Step-wise Interpretable Fine-grained Visual Categorizationby Danning Lao, Qi Liu, Jiazi…