The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models

6 March 2024

Papers citing "The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models"

5 / 5 papers shown

Title
Identifying Sub-networks in Neural Networks via Functionally Similar Representations Tian Gao Amit Dhurandhar K. Ramamurthy Dennis L. Wei 43 0 0 21 Oct 2024
Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis Guang-Da Liu Haitao Mao Jiliang Tang K. Johnson LRM 46 8 0 21 Jul 2024
Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformers Kabir Ahuja Vidhisha Balachandran Madhur Panwar Tianxing He Noah A. Smith Navin Goyal Yulia Tsvetkov 41 8 0 25 Apr 2024
Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications Boyi Wei Kaixuan Huang Yangsibo Huang Tinghao Xie Xiangyu Qi Mengzhou Xia Prateek Mittal Mengdi Wang Peter Henderson AAML 57 79 0 07 Feb 2024
Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics Prajjwal Bhargava Aleksandr Drozd Anna Rogers 98 101 0 04 Oct 2021