English
Related papers

Related papers: Test-Time Safety Alignment

200 papers

Text autoencoders are commonly used for conditional generation tasks such as style transfer. We propose methods which are plug and play, where any pretrained autoencoder can be used, and only require learning a mapping within the…

Computation and Language · Computer Science 2020-10-13 Florian Mai , Nikolaos Pappas , Ivan Montero , Noah A. Smith , James Henderson

The safety of large language models (LLMs) has increasingly emerged as a fundamental aspect of their development. Existing safety alignment for LLMs is predominantly achieved through post-training methods, which are computationally…

Artificial Intelligence · Computer Science 2026-02-03 Sicheng Shen , Mingyang Lv , Han Shen , Jialin Wu , Binghao Wang , Zhou Yang , Guobin Shen , Dongcheng Zhao , Feifei Zhao , Yi Zeng

Imitation learning is a promising approach to end-to-end training of autonomous vehicle controllers. Typically the driving process with such approaches is entirely automatic and black-box, although in practice it is desirable to control the…

Robotics · Computer Science 2020-11-23 Renhao Wang , Adam Scibior , Frank Wood

Word and sentence embeddings are useful feature representations in natural language processing. However, intrinsic evaluation for embeddings lags far behind, and there has been no significant update since the past decade. Word and sentence…

Computation and Language · Computer Science 2022-03-22 Bin Wang , C. -C. Jay Kuo , Haizhou Li

In recent years, word embeddings have been widely used to measure biases in texts. Even if they have proven to be effective in detecting a wide variety of biases, metrics based on word embeddings lack transparency and interpretability. We…

Computation and Language · Computer Science 2023-07-19 Francisco Valentini , Germán Rosati , Damián Blasi , Diego Fernandez Slezak , Edgar Altszyler

We propose an unsupervised method to obtain cross-lingual embeddings without any parallel data or pre-trained word embeddings. The proposed model, which we call multilingual neural language models, takes sentences of multiple languages as…

Computation and Language · Computer Science 2018-09-10 Takashi Wada , Tomoharu Iwata

Vision-Language Models (VLMs) can perform zero-shot classification but are susceptible to adversarial attacks. While robust fine-tuning improves their robustness, existing approaches align fixed text embeddings with an image embedding,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Junhao Dong , Yifei Zhang , Hao Zhu , Yew-Soon Ong , Piotr Koniusz

Warning: This paper contains examples of harmful language, and reader discretion is recommended. The increasing open release of powerful large language models (LLMs) has facilitated the development of downstream applications by reducing the…

Computation and Language · Computer Science 2023-10-05 Xianjun Yang , Xiao Wang , Qi Zhang , Linda Petzold , William Yang Wang , Xun Zhao , Dahua Lin

Understanding and addressing potential safety alignment risks in large language models (LLMs) is critical for ensuring their safe and trustworthy deployment. In this paper, we highlight an insidious safety threat: a compromised LLM can…

Machine Learning · Computer Science 2026-03-24 Guangnian Wan , Xinyin Ma , Gongfan Fang , Xinchao Wang

This paper evaluates existing and newly proposed answer selection methods based on pre-trained word embeddings. Word embeddings are highly effective in various natural language processing tasks and their integration into traditional…

Information Retrieval · Computer Science 2017-08-16 Rishav Chakravarti , Jiri Navratil , Cicero Nogueira dos Santos

There have been many successful applications of sentence embedding methods. However, it has not been well understood what properties are captured in the resulting sentence embeddings depending on the supervision signals. In this paper, we…

Computation and Language · Computer Science 2022-06-13 Hayato Tsukagoshi , Ryohei Sasano , Koichi Takeda

Existing studies in backdoor defense have predominantly focused on the training phase, overlooking the critical aspect of testing time defense. This gap becomes pronounced in the context of LLMs deployed as Web Services, which typically…

Computation and Language · Computer Science 2025-02-13 Wenjie Mo , Jiashu Xu , Qin Liu , Jiongxiao Wang , Jun Yan , Hadi Askari , Chaowei Xiao , Muhao Chen

This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insights for developing more secure and reliable AI systems. We…

Computation and Language · Computer Science 2026-02-25 Xing Li , Hui-Ling Zhen , Lihao Yin , Xianzhi Yu , Zhenhua Dong , Mingxuan Yuan

Recent advancements in large language models (LLMs) have accelerated progress toward artificial general intelligence, yet their potential to generate harmful content poses critical safety challenges. Existing alignment methods often…

Computation and Language · Computer Science 2025-10-08 Kehua Feng , Keyan Ding , Yuhao Wang , Menghan Li , Fanjunduo Wei , Xinda Wang , Qiang Zhang , Huajun Chen

Self-modulating mechanisms introduce dynamic adaptation capabilities within language models through contextual realignment strategies that influence token embedding trajectories across extended sequences. Contextual Flux is explored as an…

Computation and Language · Computer Science 2025-08-11 Henry Evidail , Zachary Mountebank , Alistair Hathersage , Peter Stanhope , Basil Ravenscroft , Tobias Waddingham

Reasoning-based language models have demonstrated strong performance across various domains, with the most notable gains seen in mathematical and coding tasks. Recent research has shown that reasoning also offers significant benefits for…

Artificial Intelligence · Computer Science 2025-05-27 Makesh Narsimhan Sreedhar , Traian Rebedea , Christopher Parisien

Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of unsafe behaviors while evading detection during normal interactions. The high dimensionality of potential triggers in the token space and the diverse…

Cryptography and Security · Computer Science 2024-06-26 Yi Zeng , Weiyu Sun , Tran Ngoc Huynh , Dawn Song , Bo Li , Ruoxi Jia

Conventional text classification models make a bag-of-words assumption reducing text into word occurrence counts per document. Recent algorithms such as word2vec are capable of learning semantic meaning and similarity between words in an…

Computation and Language · Computer Science 2018-07-11 Vincent Major , Alisa Surkis , Yindalon Aphinyanaphongs

Text embedding models from Natural Language Processing can map text data (e.g. words, sentences, documents) to supposedly meaningful numerical representations (a.k.a. text embeddings). While such models are increasingly applied in social…

Computers and Society · Computer Science 2023-01-24 Qixiang Fang , Dong Nguyen , Daniel L Oberski

In text-to-image diffusion models, the cross-attention map of each text token indicates the specific image regions attended. Comparing these maps of syntactically related tokens provides insights into how well the generated image reflects…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Jeeyung Kim , Erfan Esmaeili , Qiang Qiu