English
Related papers

Related papers: Test-time Augmentation for Factual Probing

200 papers

Reasoning quality in large language models depends not only on producing correct answers but also on generating valid intermediate steps. We study this through multiple-choice question answering (MCQA), which provides a controlled setting…

Artificial Intelligence · Computer Science 2025-10-01 Raphael Schumann , Stefan Riezler

Despite recent advancements in Machine Learning, many tasks still involve working in low-data regimes which can make solving natural language problems difficult. Recently, a number of text augmentation techniques have emerged in the field…

Computation and Language · Computer Science 2023-02-27 Congcong Wang , Gonzalo Fiz Pontiveros , Steven Derby , Tri Kurniawan Wijaya

Pretrained language models can be effectively stimulated by textual prompts or demonstrations, especially in low-data scenarios. Recent works have focused on automatically searching discrete or continuous prompts or optimized verbalizers,…

Computation and Language · Computer Science 2023-09-20 Xiaozhuan Liang , Ningyu Zhang , Siyuan Cheng , Zhenru Zhang , Chuanqi Tan , Huajun Chen

For CLIP-based prompt tuning, introducing more data as additional knowledge for enhancing fine-tuning process is proved to be an effective approach. Existing data amplification strategies for prompt tuning typically rely on external…

Computer Vision and Pattern Recognition · Computer Science 2025-11-13 Haoyang Li , Liang Wang , Chao Wang , Siyu Zhou , Jing Jiang , Yan Peng , Guodong Long

Test-time adaptation (TTA) enables efficient adaptation of deployed models, yet it often leads to poorly calibrated predictive uncertainty - a critical issue in high-stakes domains such as autonomous driving, finance, and healthcare.…

Machine Learning · Computer Science 2025-12-09 Gilhyun Nam , Taewon Kim , Joonhyun Jeong , Eunho Yang

Large language models (LLMs) are prone to generating factually incorrect outputs. Recent work has applied conformal prediction to provide uncertainty estimates and statistical guarantees for the factuality of LLM generations. However,…

Computation and Language · Computer Science 2026-04-16 Aleksandr Rubashevskii , Dzianis Piatrashyn , Preslav Nakov , Maxim Panov

Data augmentation is a powerful technique to enhance the performance of a deep learning task but has received less attention in 3D deep learning. It is well known that when 3D shapes are sparsely represented with low point density, the…

Computer Vision and Pattern Recognition · Computer Science 2023-11-23 Tuan-Anh Vu , Srinjay Sarkar , Zhiyuan Zhang , Binh-Son Hua , Sai-Kit Yeung

Large language models are widely used across domains, yet there are concerns about their factual reliability and biases. Factual knowledge probing offers a systematic means to evaluate these aspects. Most existing benchmarks focus on…

Computation and Language · Computer Science 2025-12-15 Evren Ayberk Munis , Deniz Yılmaz , Arianna Muti , Çağrı Toraman

Inspecting Chain-of-Thought reasoning is among the most common means of understanding why an LLM produced its output. But well-known problems with CoT faithfulness severely limit what insights can be gained from this practice. In this…

Artificial Intelligence · Computer Science 2026-02-25 Peter Hase , Christopher Potts

Pre-trained vision-language models (e.g., CLIP) have shown promising zero-shot generalization in many downstream tasks with properly designed text prompts. Instead of relying on hand-engineered prompts, recent works learn prompts using the…

Computer Vision and Pattern Recognition · Computer Science 2022-09-16 Manli Shu , Weili Nie , De-An Huang , Zhiding Yu , Tom Goldstein , Anima Anandkumar , Chaowei Xiao

Large Language Models (LLMs) exhibit impressive results across a wide range of natural language processing (NLP) tasks, yet they can often produce factually incorrect outputs. This paper introduces a simple but effective low-latency…

Computation and Language · Computer Science 2024-10-22 Changmao Li , Jeffrey Flanigan

Large language models (LLMs), such as ChatGPT, are able to generate human-like, fluent responses for many downstream tasks, e.g., task-oriented dialog and question answering. However, applying LLMs to real-world, mission-critical…

Computation and Language · Computer Science 2023-03-10 Baolin Peng , Michel Galley , Pengcheng He , Hao Cheng , Yujia Xie , Yu Hu , Qiuyuan Huang , Lars Liden , Zhou Yu , Weizhu Chen , Jianfeng Gao

Test-time domain adaptation aims to adapt a source pre-trained model to a target domain without using any source data. Existing works mainly consider the case where the target domain is static. However, real-world machine perception systems…

Computer Vision and Pattern Recognition · Computer Science 2022-03-28 Qin Wang , Olga Fink , Luc Van Gool , Dengxin Dai

Continual Test-Time Adaptation (CTTA) aims to adapt a pre-trained model to a sequence of target domains during the test phase without accessing the source data. To adapt to unlabeled data from unknown domains, existing methods rely on…

Machine Learning · Computer Science 2024-07-15 Jiayao Tan , Fan Lyu , Chenggong Ni , Tingliang Feng , Fuyuan Hu , Zhang Zhang , Shaochuang Zhao , Liang Wang

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,…

Machine Learning · Computer Science 2025-07-11 Xiaoling Zhou , Ou Wu , Michael K. Ng

Test-time training (TTT) has recently emerged as a promising method to improve the reasoning abilities of large language models (LLMs), in which the model directly learns from test data without access to labels. However, this reliance on…

Machine Learning · Computer Science 2026-03-17 Vanshaj Khattar , Md Rafi ur Rashid , Moumita Choudhury , Jing Liu , Toshiaki Koike-Akino , Ming Jin , Ye Wang

Language models (LMs) have shown impressive performance on tasks within their training distribution, but often struggle with structurally novel tasks even when given a small number of in-context task examples. We investigate the…

Artificial Intelligence · Computer Science 2025-03-26 Ekin Akyürek , Mehul Damani , Adam Zweiger , Linlu Qiu , Han Guo , Jyothish Pari , Yoon Kim , Jacob Andreas

Chain-of-thought (CoT) prompting reliably improves language-model accuracy, but which properties of a rationale text drive the improvement is poorly understood. Prior work has largely studied generation-time behavior. We instead ask a…

Artificial Intelligence · Computer Science 2026-05-27 Xiang Wang , Wei Wei

The inevitable appearance of spurious correlations in training datasets hurts the generalization of NLP models on unseen data. Previous work has found that datasets with paired inputs are prone to correlations between a specific part of the…

Computation and Language · Computer Science 2024-10-10 Yanai Elazar , Bhargavi Paranjape , Hao Peng , Sarah Wiegreffe , Khyathi Raghavi , Vivek Srikumar , Sameer Singh , Noah A. Smith

Language models can be prompted to reason through problems in a manner that significantly improves performance. However, \textit{why} such prompting improves performance is unclear. Recent work showed that using logically \textit{invalid}…

Artificial Intelligence · Computer Science 2023-07-25 Rylan Schaeffer , Kateryna Pistunova , Samar Khanna , Sarthak Consul , Sanmi Koyejo
‹ Prev 1 8 9 10 Next ›