activity
20212023
most citedAutomatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies

24 citations · 38 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CL20231 cited

SiRA: Sparse Mixture of Low Rank Adaptation

Yun Zhu, Nevan Wichers, Chu-Cheng Lin +8

Parameter Efficient Tuning has been an prominent approach to adapt the Large Language Model to downstream tasks. Most previous works considers adding the dense trainable parameters…

cs.CL2023

FIAT: Fusing learning paradigms with Instruction-Accelerated Tuning

Xinyi Wang, John Wieting, Jonathan H. Clark

Learning paradigms for large language models (LLMs) currently tend to fall within either in-context learning (ICL) or full fine-tuning. Each of these comes with their own trade-off…

cs.CL202324 cited

Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies

Liangming Pan, Michael Saxon, Wenda Xu +3

Large language models (LLMs) have demonstrated remarkable performance across a wide array of NLP tasks. However, their efficacy is undermined by undesired and inconsistent behavior…

cs.LG20232 cited

Non-parametric Probabilistic Time Series Forecasting via Innovations Representation

Xinyi Wang, Meijen Lee, Qing Zhao +1

Probabilistic time series forecasting predicts the conditional probability distributions of the time series at a future time given past realizations. Such techniques are critical i…

cs.LG2022

Semantic Preserving Adversarial Attack Generation with Autoencoder and Genetic Algorithm

Xinyi Wang, Simon Yusuf Enoch, Dong Seong Kim

Widely used deep learning models are found to have poor robustness. Little noises can fool state-of-the-art models into making incorrect predictions. While there is a great deal of…

cs.CL202111 cited

Gradient-guided Loss Masking for Neural Machine Translation

Xinyi Wang, Ankur Bapna, Melvin Johnson +1

To mitigate the negative effect of low quality training data on the performance of neural machine translation models, most existing strategies focus on filtering out harmful data b…