paper-with-me

Papers

Logit Separability-Driven Samples and Multiple Class-Related Words Selection for Advancing In-Context Learning

2024-06-16 · Zhu Zixiao, Feng Zijian, Zhou Hanzhang, Qian Junlang, Mao Kezhi

Effective organization of in-context learning (ICL) demonstrations is key to improving the quality of large language model (LLM) responses. To create better sample-label pairs that instruct LLM understanding, we introduce logit separability, a criterion to assess the clarity of both samples and class-related words at the logit level. This facilitates the optimization of sample and label selection, enhancing the precision of information provided in ICL demonstrations. Additionally, we find that incorporating multiple class-related words for each sample, rather than relying on a single class name, improves performance by offering a broader range of label information. Building on these insights, we propose LICL, a logit separability-based method that jointly organizes samples and integrates multiple class-related words into each sample-label pair. Evaluations across seven classification datasets show that this approach significantly improves ICL performance by providing clearer instructions and richer label information.

📄 PDF Abstract BibTeX arXiv:2406.10908

Code (1)

midiyazhu/micl 공식 구현 pytorch

Tasks

In-Context LearningLanguage ModelingLanguage ModellingLarge Language Model

Similar Papers 제목 키워드 기반

Revisiting Logit Distributions for Reliable Out-of-Distribution Detection

2025-10-23 · Jiachen Liang, Ruibing Hou, Minyang Hu, Hong Chang 외 arxiv

Out-of-distribution (OOD) detection is critical for ensuring the reliability of deep learning models in open-world applications. While post-hoc methods are favored for their efficiency and ease of deployment, existing ap…

Out-of-Distribution Detection

Enhancing Out-of-Distribution Detection with Extended Logit Normalization

2025-04-15 · Yifan Ding, Xixi Liu, Jonas Unger, Gabriel Eilertsen

Out-of-distribution (OOD) detection is essential for the safe deployment of machine learning models. Recent advances have explored improved classification losses and representation learning strategies to enhance OOD dete…

Out-of-Distribution DetectionOut of Distribution (OOD) DetectionRepresentation Learning

Unleashing the Potential of All Test Samples: Mean-Shift Guided Test-Time Adaptation

2025-07-01 · Jizhou Han, Chenhao Ding, SongLin Dong, Yuhang He 외 arxiv

Visual-language models (VLMs) like CLIP exhibit strong generalization but struggle with distribution shifts at test time. Existing training-free test-time adaptation (TTA) methods operate strictly within CLIP's original …

Test-time Adaptation

Reject Illegal Inputs with Generative Classifier Derived from Any Discriminative Classifier

2020-01-02 · Xin Wang

Generative classifiers have been shown promising to detect illegal inputs including adversarial examples and out-of-distribution samples. Supervised Deep Infomax~(SDIM) is a scalable end-to-end framework to learn generat…

Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement

2026-07-29 · Tianyan Deng, Yanxiong Li, Rui Gao, Jiahao Du arxiv

Few-shot Open-set audio classification requires classifying query samples from known classes with a few labeled support samples while rejecting query samples from unknown classes. Transductive inference jointly observes …

Audio Classification