paper-with-me

홈 › Papers

Unsupervised Calibration through Prior Adaptation for Text Classification using Large Language Models

2023-07-13 · Lautaro Estienne, Luciana Ferrer, Matías Vera, Pablo Piantanida

A wide variety of natural language tasks are currently being addressed with large-scale language models (LLMs). These models are usually trained with a very large amount of unsupervised text data and adapted to perform a downstream natural language task using methods like fine-tuning, calibration or in-context learning. In this work, we propose an approach to adapt the prior class distribution to perform text classification tasks without the need for labelled samples and only few in-domain sample queries. The proposed approach treats the LLM as a black box, adding a stage where the model posteriors are calibrated to the task. Results show that these methods outperform the un-adapted model for different number of training shots in the prompt and a previous approach were calibration is performed without using any adaptation data.

📄 PDF Abstract BibTeX arXiv:2307.06713

Code (1)

LautaroEst/efficient-reestimation pytorch

Tasks

In-Context Learningtext-classificationText Classification

Similar Papers 제목 키워드 기반

Uncertainty-Aware (Un)Supervised Few-Shot User Adaptation for On-Device Personalized Human Activity Recognition

2026-06-03 · Maximilian Burzer, Till Riedel, Michael Beigl, Tobias Röddiger arxiv

Sensor-based Human Activity Recognition (HAR) models often degrade on unseen users due to domain shifts caused by individual movement patterns and sensor placement. Practical wearable HAR systems therefore require person…

Human Activity Recognition

Test Time Adaptation Using Adaptive Quantile Recalibration

2025-11-05 · Paria Mehrbod, Pedro Vianna, Geraldin Nanfack, Guy Wolf 외 arxiv

Domain adaptation is a key strategy for enhancing the generalizability of deep learning models in real-world scenarios, where test distributions often diverge significantly from the training domain. However, conventional…

Test-time AdaptationDomain Adaptation

UMFC: Unsupervised Multi-Domain Feature Calibration for Vision-Language Models

2024-11-11 · Jiachen Liang, Ruibing Hou, Minyang Hu, Hong Chang 외

Pre-trained vision-language models (e.g., CLIP) have shown powerful zero-shot transfer capabilities. But they still struggle with domain shifts and typically require labeled data to adapt to downstream tasks, which could…

Test-time AdaptationTransductive Learning

PseudoCal: A Source-Free Approach to Unsupervised Uncertainty Calibration in Domain Adaptation

2023-07-14 · Dapeng Hu, Jian Liang, Xinchao Wang, Chuan-Sheng Foo

Unsupervised domain adaptation (UDA) has witnessed remarkable advancements in improving the accuracy of models for unlabeled target domains. However, the calibration of predictive uncertainty in the target domain, a cruc…

Domain AdaptationUnsupervised Domain Adaptation

AUGCAL: Improving Sim2Real Adaptation by Uncertainty Calibration on Augmented Synthetic Images

2023-12-11 · Prithvijit Chattopadhyay, Bharat Goyal, Boglarka Ecsedi, Viraj Prabhu 외

Synthetic data (SIM) drawn from simulators have emerged as a popular alternative for training models where acquiring annotated real-world images is difficult. However, transferring models trained on synthetic images to r…

Domain AdaptationUnsupervised Domain Adaptation