paper-with-me

홈 › Papers

Fine-Tuning Deteriorates General Textual Out-of-Distribution Detection by Distorting Task-Agnostic Features

2023-01-30 · Sishuo Chen, Wenkai Yang, Xiaohan Bi, Xu sun

Detecting out-of-distribution (OOD) inputs is crucial for the safe deployment of natural language processing (NLP) models. Though existing methods, especially those based on the statistics in the feature space of fine-tuned pre-trained language models (PLMs), are claimed to be effective, their effectiveness on different types of distribution shifts remains underexplored. In this work, we take the first step to comprehensively evaluate the mainstream textual OOD detection methods for detecting semantic and non-semantic shifts. We find that: (1) no existing method behaves well in both settings; (2) fine-tuning PLMs on in-distribution data benefits detecting semantic shifts but severely deteriorates detecting non-semantic shifts, which can be attributed to the distortion of task-agnostic features. To alleviate the issue, we present a simple yet effective general OOD score named GNOME that integrates the confidence scores derived from the task-agnostic and task-specific representations. Experiments show that GNOME works well in both semantic and non-semantic shift scenarios, and further brings significant improvement on two cross-task benchmarks where both kinds of shifts simultaneously take place. Our code is available at https://github.com/lancopku/GNOME.

📄 PDF Abstract BibTeX arXiv:2301.12715

Code (2)

lancopku/gnome 공식 구현
lancopku/avg-avg pytorch

Tasks

Out-of-Distribution DetectionOut of Distribution (OOD) Detection

Similar Papers 제목 키워드 기반

PoGDiff: Product-of-Gaussians Diffusion Models for Imbalanced Text-to-Image Generation

2025-02-12 · Ziyan Wang, Sizhe Wei, Xiaoming Huo, Hao Wang

Diffusion models have made significant advancements in recent years. However, their performance often deteriorates when trained or fine-tuned on imbalanced datasets. This degradation is largely due to the disproportionat…

Image GenerationText to Image GenerationText-to-Image Generation

Exploring Diffusion Models' Corruption Stage in Few-Shot Fine-tuning and Mitigating with Bayesian Neural Networks

2024-05-30 · Xiaoyu Wu, Jiaru Zhang, Yang Hua, Bohan Lyu 외

Few-shot fine-tuning of Diffusion Models (DMs) is a key advancement, significantly reducing training costs and enabling personalized AI applications. However, we explore the training dynamics of DMs and observe an unanti…

Variational Inference

Prompt Combines Paraphrase: Teaching Pre-trained Models to Understand Rare Biomedical Words

2022-09-14 · COLING 2022 10 · Haochun Wang, Chi Liu, Nuwa Xi, Sendong Zhao 외

Prompt-based fine-tuning for pre-trained models has proven effective for many natural language processing tasks under few-shot settings in general domain. However, tuning with prompt in biomedical domain has not been inv…

Natural Language Inference

Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks

2023-09-29 · Hao Chen, Jindong Wang, Ankit Shah, Ran Tao 외

Pre-training on large-scale datasets and then fine-tuning on downstream tasks have become a standard practice in deep learning. However, pre-training data often contain label noise that may adversely affect the generaliz…

Learning to Modulate pre-trained Models in RL

2023-06-26 · NeurIPS 2023 11 · Thomas Schmied, Markus Hofmarcher, Fabian Paischer, Razvan Pascanu 외

Reinforcement Learning (RL) has been successful in various domains like robotics, game playing, and simulation. While RL agents have shown impressive capabilities in their specific tasks, they insufficiently adapt to new…

Reinforcement Learning (RL)