中文
相关论文

相关论文: Prompt Tuning Pushes Farther, Contrastive Learning…

200 篇论文

Trained classification models can unintentionally lead to biased representations and predictions, which can reinforce societal preconceptions and stereotypes. Existing debiasing methods for classification models, such as adversarial…

计算与语言 · 计算机科学 2021-09-23 Aili Shen , Xudong Han , Trevor Cohn , Timothy Baldwin , Lea Frermann

Large language models (LLMs) excel in natural language processing but adapting these LLMs to speech processing tasks efficiently is not straightforward. Direct task-specific fine-tuning is limited by overfitting risks, data requirements,…

计算与语言 · 计算机科学 2025-06-02 Maike Züfle , Jan Niehues

Representation learning has significantly been developed with the advance of contrastive learning methods. Most of those methods have benefited from various data augmentations that are carefully designated to maintain their identities so…

计算机视觉与模式识别 · 计算机科学 2022-01-24 Xiao Wang , Guo-Jun Qi

Speech models may be affected by performance imbalance in different population subgroups, raising concerns about fair treatment across these groups. Prior attempts to mitigate unfairness either focus on user-defined subgroups, potentially…

计算与语言 · 计算机科学 2024-09-17 Alkis Koudounas , Flavio Giobergia , Eliana Pastor , Elena Baralis

Recent studies have revealed that the widely-used Pre-trained Language Models (PLMs) propagate societal biases from the large unmoderated pre-training corpora. Existing solutions require debiasing training processes and datasets for…

计算与语言 · 计算机科学 2023-07-25 Somayeh Ghanbarzadeh , Yan Huang , Hamid Palangi , Radames Cruz Moreno , Hamed Khanpour

Counterfactual data augmentation (CDA) is a method for controlling information or biases in training datasets by generating a complementary dataset with typically opposing biases. Prior work often either relies on hand-crafted rules or…

机器学习 · 计算机科学 2025-02-26 Mitchell Plyler , Min Chi

Stance detection classifies stance relations (namely, Favor, Against, or Neither) between comments and targets. Pretrained language models (PLMs) are widely used to mine the stance relation to improve the performance of stance detection…

机器学习 · 计算机科学 2024-05-21 Jiarui Zhang , Shaojuan Wu , Xiaowang Zhang , Zhiyong Feng

Counterfactual data augmentation has recently emerged as a method to mitigate confounding biases in the training data. These biases, such as spurious correlations, arise due to various observed and unobserved confounding variables in the…

Contrastive learning models have demonstrated impressive abilities to capture semantic similarities by aligning representations in the embedding space. However, their performance can be limited by the quality of the training data and its…

计算机视觉与模式识别 · 计算机科学 2025-03-27 Amirabbas Afzali , Borna Khodabandeh , Ali Rasekh , Mahyar JafariNodeh , Sepehr kazemi , Simon Gottschalk

Machine learning models are prone to capturing the spurious correlations between non-causal attributes and classes, with counterfactual data augmentation being a promising direction for breaking these spurious associations. However,…

机器学习 · 计算机科学 2025-07-11 Xiaoling Zhou , Ou Wu , Michael K. Ng

Prompting shows promising results in few-shot scenarios. However, its strength for multilingual/cross-lingual problems has not been fully exploited. Zhao and Sch\"utze (2021) made initial explorations in this direction by presenting that…

计算与语言 · 计算机科学 2023-05-25 Meng Zhou , Xin Li , Yue Jiang , Lidong Bing

Learning sentence embeddings in an unsupervised manner is fundamental in natural language processing. Recent common practice is to couple pre-trained language models with unsupervised contrastive learning, whose success relies on augmenting…

计算与语言 · 计算机科学 2022-10-20 Qiyu Wu , Chongyang Tao , Tao Shen , Can Xu , Xiubo Geng , Daxin Jiang

Despite their impressive performance in a wide range of NLP tasks, Large Language Models (LLMs) have been reported to encode worrying-levels of gender biases. Prior work has proposed debiasing methods that require human labelled examples,…

计算与语言 · 计算机科学 2024-02-21 Daisuke Oba , Masahiro Kaneko , Danushka Bollegala

Using responses generated by high-performing large language models (LLMs) for instruction tuning has become a widely adopted approach. However, the existing literature overlooks a property of LLM-generated responses: they conflate world…

计算与语言 · 计算机科学 2026-04-16 Tatsuya Ichinose , Youmi Ma , Masanari Oi , Ryuto Koike , Naoaki Okazaki

Counterfactual Data Augmentation (CDA) is a commonly used technique for improving robustness in natural language classifiers. However, one fundamental challenge is how to discover meaningful counterfactuals and efficiently label them, with…

计算与语言 · 计算机科学 2023-05-24 Ananth Balashankar , Xuezhi Wang , Yao Qin , Ben Packer , Nithum Thain , Jilin Chen , Ed H. Chi , Alex Beutel

Frontier Large Language Models (LLMs) can be socially discriminatory or sensitive to spurious features of their inputs. Because only well-resourced corporations can train frontier LLMs, we need robust test-time strategies to control such…

计算与语言 · 计算机科学 2024-10-08 Leonardo Cotta , Chris J. Maddison

Contrastive learning-based recommendation algorithms have significantly advanced the field of self-supervised recommendation, particularly with BPR as a representative ranking prediction task that dominates implicit collaborative filtering.…

信息检索 · 计算机科学 2024-03-13 Shipeng Song , Bin Liu , Fei Teng , Tianrui Li

Language models (LMs) trained on vast quantities of unlabelled data have greatly advanced the field of natural language processing (NLP). In this study, we re-visit the widely accepted notion in NLP that continued pre-training LMs on…

计算与语言 · 计算机科学 2023-10-09 Zhengxiang Shi , Aldo Lipani

We examine whether neural natural language processing (NLP) systems reflect historical biases in training data. We define a general benchmark to quantify gender bias in a variety of neural NLP tasks. Our empirical evaluation with…

计算与语言 · 计算机科学 2019-06-03 Kaiji Lu , Piotr Mardziel , Fangjing Wu , Preetam Amancharla , Anupam Datta

Several automatic approaches for objective music performance assessment (MPA) have been proposed in the past, however, existing systems are not yet capable of reliably predicting ratings with the same accuracy as professional judges. This…

声音 · 计算机科学 2021-08-16 Pavan Seshadri , Alexander Lerch