English
Related papers

Related papers: Contrastive Weak-to-strong Generalization

200 papers

Large language models (LLMs) are trained on huge amounts of textual data, and concerns have been raised that the limits of such data may soon be reached. A potential solution is to train on synthetic data sampled from LLMs. In this work, we…

Computation and Language · Computer Science 2025-10-10 Jannek Ulm , Kevin Du , Vésteinn Snæbjarnarson

Widely used alignment techniques, such as reinforcement learning from human feedback (RLHF), rely on the ability of humans to supervise model behavior - for example, to evaluate whether a model faithfully followed instructions or generated…

Recently, contrastive learning has been shown to be effective in improving pre-trained language models (PLM) to derive high-quality sentence representations. It aims to pull close positive examples to enhance the alignment while push apart…

Computation and Language · Computer Science 2022-05-03 Kun Zhou , Beichen Zhang , Wayne Xin Zhao , Ji-Rong Wen

Better disentanglement of speech representation is essential to improve the quality of voice conversion. Recently contrastive learning is applied to voice conversion successfully based on speaker labels. However, the performance of model…

Sound · Computer Science 2023-11-16 Yimin Deng , Xulong Zhang , Jianzong Wang , Ning Cheng , Jing Xiao

While Contrastive Decoding (CD) has proven effective at enhancing Large Audio Language Models (LALMs), the underlying mechanisms driving its success and the comparative efficacy of different strategies remain unclear. This study…

Sound · Computer Science 2026-03-11 Tzu-Quan Lin , Wei-Ping Huang , Yi-Cheng Lin , Hung-yi Lee

With the widespread application of Large Language Models (LLMs), it has become a significant concern to ensure their safety and prevent harmful responses. While current safe-alignment methods based on instruction fine-tuning and…

Computation and Language · Computer Science 2025-12-16 Xiaoyun Zhang , Zhengyue Zhao , Wenxuan Shi , Kaidi Xu , Di Huang , Xing Hu

The generation of toxic content by large language models (LLMs) remains a critical challenge for the safe deployment of language technology. We propose a novel framework for implicit knowledge editing and controlled text generation by…

Computation and Language · Computer Science 2025-06-02 Tassilo Klein , Moin Nabi

Weak-to-strong (W2S) generalization, in which a strong model is fine-tuned on outputs of a weaker, task-specialized model, has been proposed as an approach to aligning superhuman AI systems. Existing theoretical analyses either fix the…

Machine Learning · Statistics 2026-05-14 Ryoya Awano , Taiji Suzuki

Prevailing methods for training Large Language Models (LLMs) as text encoders rely on contrastive losses that treat the model as a black box function, discarding its generative and reasoning capabilities in favor of static embeddings. We…

Computation and Language · Computer Science 2025-10-07 Jiashuo Sun , Shixuan Liu , Zhaochen Su , Xianrui Zhong , Pengcheng Jiang , Bowen Jin , Peiran Li , Weijia Shi , Jiawei Han

Contrastive Learning (CL) has emerged as a dominant technique for unsupervised representation learning which embeds augmented versions of the anchor close to each other (positive samples) and pushes the embeddings of other samples…

Artificial Intelligence · Computer Science 2022-06-15 Jun Xia , Lirong Wu , Ge Wang , Jintao Chen , Stan Z. Li

Weak-to-strong generalization, where weakly supervised strong models outperform their weaker teachers, offers a promising approach to aligning superhuman models with human values. To deepen the understanding of this approach, we provide…

Machine Learning · Computer Science 2025-06-05 Wei Yao , Wenkai Yang , Gengze Xu , Ziqiao Wang , Yankai Lin , Yong Liu

Fine-tuned pre-trained language models (LMs) have achieved enormous success in many natural language processing (NLP) tasks, but they still require excessive labeled data in the fine-tuning stage. We study the problem of fine-tuning…

Computation and Language · Computer Science 2021-04-01 Yue Yu , Simiao Zuo , Haoming Jiang , Wendi Ren , Tuo Zhao , Chao Zhang

Contemporary large-scale visual language models (VLMs) exhibit strong representation capacities, making them ubiquitous for enhancing image and text understanding tasks. They are often trained in a contrastive manner on a large and diverse…

Computer Vision and Pattern Recognition · Computer Science 2023-11-08 Ugur Sahin , Hang Li , Qadeer Khan , Daniel Cremers , Volker Tresp

Deep learning with noisy labels is an interesting challenge in weakly supervised learning. Despite their significant learning capacity, CNNs have a tendency to overfit in the presence of samples with noisy labels. Alleviating this issue,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-06 Yan Han , Soumava Kumar Roy , Mehrtash Harandi , Lars Petersson

Vision-language (VL) models often exhibit a limited understanding of complex expressions of visual objects (e.g., attributes, shapes, and their relations), given complex and diverse language queries. Traditional approaches attempt to…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Kwanyong Park , Kuniaki Saito , Donghyun Kim

Cross-lingual summarization (CLS) is a sophisticated branch in Natural Language Processing that demands models to accurately translate and summarize articles from different source languages. Despite the improvement of the subsequent…

Computation and Language · Computer Science 2024-11-27 Sanzana Karim Lora , M. Sohel Rahman , Rifat Shahriyar

Deep Learning (DL) models to analyze source code have shown immense promise during the past few years. More recently, self-supervised pre-training has gained traction for learning generic code representations valuable for many downstream SE…

Software Engineering · Computer Science 2023-06-07 Yangruibo Ding , Saikat Chakraborty , Luca Buratti , Saurabh Pujar , Alessandro Morari , Gail Kaiser , Baishakhi Ray

Current debiasing approaches often result a degradation in model capabilities such as factual accuracy and knowledge retention. Through systematic evaluation across multiple benchmarks, we demonstrate that existing debiasing methods face…

Machine Learning · Computer Science 2025-05-27 Buse Sibel Korkmaz , Rahul Nair , Elizabeth M. Daly , Antonio del Rio Chanona

Contrastive learning has achieved remarkable success in learning effective representations, with supervised contrastive learning often outperforming self-supervised approaches. However, in real-world scenarios, data annotations are often…

Machine Learning · Computer Science 2025-05-29 Zi-Hao Zhou , Jun-Jie Wang , Tong Wei , Min-Ling Zhang

Contrastive learning has been shown to produce generalizable representations of audio and visual data by maximizing the lower bound on the mutual information (MI) between different views of an instance. However, obtaining a tight lower…

Machine Learning · Computer Science 2021-04-20 Shuang Ma , Zhaoyang Zeng , Daniel McDuff , Yale Song