1 citations · 1 across the 4 of their papers we have counts for
5 papers
Will it Merge? On The Causes of Model Mergeability
Adir Rahamim, Asaf Yehudai, Boaz Carmeli +3
Model merging has emerged as a promising technique for combining multiple fine-tuned models into a single multitask model without retraining. However, the factors that determine wh…
Growing a Tail: Increasing Output Diversity in Large Language Models
Michal Shur-Ofry, Bar Horowitz-Amsalem, Adir Rahamim +1
How diverse are the outputs of large language models when diversity is desired? We examine the diversity of responses of several language models to questions with multiple possible…
Fast Forwarding Low-Rank Training
Adir Rahamim, Naomi Saphra, Sara Kangaslahti +1
Parameter efficient finetuning methods like low-rank adaptation (LoRA) aim to reduce the computational costs of finetuning pretrained Language Models (LMs). Enabled by these low-ra…
ContraSim -- Analyzing Neural Representations Based on Contrastive Learning
Adir Rahamim, Yonatan Belinkov
Recent work has compared neural network representations via similarity-based analyses to improve model interpretation. The quality of a similarity measure is typically evaluated by…
Robustness through Cognitive Dissociation Mitigation in Contrastive Adversarial Training
Adir Rahamim, Itay Naeh
In this paper, we introduce a novel neural network training framework that increases model's adversarial robustness to adversarial attacks while maintaining high clean accuracy by…