most citedEfficient XAI Techniques: A Taxonomic Survey

11 citations · 15 across the 9 of their papers we have counts for

collaborators

9 papers

cs.CE2024

Assessing and Enhancing Large Language Models in Rare Disease Question-answering

Guanchu Wang, Junhao Ran, Ruixiang Tang +6

Despite the impressive capabilities of Large Language Models (LLMs) in general medical domains, questions remain about their performance in diagnosing rare diseases. To answer this…

cs.LG2024

Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity

Wentao Guo, Jikai Long, Yimeng Zeng +9

Zeroth-order optimization (ZO) is a memory-efficient strategy for fine-tuning Large Language Models using only forward passes. However, the application of ZO fine-tuning in memory-…

cs.CL20241 cited

Learning to Compress Prompt in Natural Language Formats

Yu-Neng Chuang, Tianwei Xing, Chia-Yuan Chang +3

Large language models (LLMs) are great at processing multiple natural language processing tasks, but their abilities are constrained by inferior performance with long context, slow…

cs.CL20241 cited

FFSplit: Split Feed-Forward Network For Optimizing Accuracy-Efficiency Trade-off in Language Model Inference

Zirui Liu, Qingquan Song, Qiang Charles Xiao +4

The large number of parameters in Pretrained Language Models enhance their performance, but also make them resource-intensive, making it challenging to deploy them on commodity har…

cs.LG20231 cited

Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots

Ruixiang Tang, Jiayi Yuan, Yiming Li +3

In the field of natural language processing, the prevalent approach involves fine-tuning pretrained language models (PLMs) using local samples. Recent research has exposed the susc…

cs.LG2023

Efficient GNN Explanation via Learning Removal-based Attribution

Yao Rong, Guanchu Wang, Qizhang Feng +4

As Graph Neural Networks (GNNs) have been widely used in real-world applications, model explanations are required not only by users but also by legal regulations. However, simultan…