English
Related papers

Related papers: Language-Switching Triggers Take a Latent Detour T…

200 papers

Several algorithms implemented by language models have recently been successfully reversed-engineered. However, these findings have been concentrated on specific tasks and models, leaving it unclear how universal circuits are across…

Computation and Language · Computer Science 2024-10-10 Javier Ferrando , Marta R. Costa-jussà

Backdoor attack introduces artificial vulnerabilities into the model by poisoning a subset of the training data via injecting triggers and modifying labels. Various trigger design strategies have been explored to attack text classifiers,…

Computation and Language · Computer Science 2021-09-23 Zichao Li , Dheeraj Mekala , Chengyu Dong , Jingbo Shang

We investigate how large language models perform latent multi-hop reasoning in prompts like "Wolfgang Amadeus Mozart's mother's spouse is". To analyze this process, we introduce logit flow, an interpretability method that traces how logits…

Computation and Language · Computer Science 2025-02-18 Zeping Yu , Yonatan Belinkov , Sophia Ananiadou

Large Language Models (LLMs) have achieved significantly advanced capabilities in understanding and generating human language text, which have gained increasing popularity over recent years. Apart from their state-of-the-art natural…

Cryptography and Security · Computer Science 2025-02-11 Yihe Zhou , Tao Ni , Wei-Bin Lee , Qingchuan Zhao

Recent research suggests that the feed-forward module within Transformers can be viewed as a collection of key-value memories, where the keys learn to capture specific patterns from the input based on the training examples. The values then…

Computation and Language · Computer Science 2023-10-25 Sunit Bhattacharya , Ondrej Bojar

Large Language Models (LLMs), despite their impressive capabilities, often fail to accurately repeat a single word when prompted to, and instead output unrelated text. This unexplained failure mode represents a vulnerability, allowing even…

Machine Learning · Computer Science 2025-03-13 Itay Yona , Ilia Shumailov , Jamie Hayes , Federico Barbero , Yossi Gandelsman

Natural language processing (NLP) has received unprecedented attention. While advancements in NLP models have led to extensive research into their backdoor vulnerabilities, the potential for these advancements to introduce new backdoor…

Cryptography and Security · Computer Science 2024-03-18 Ka-Ho Chow , Wenqi Wei , Lei Yu

Refusal mechanisms in large language models (LLMs) are essential for ensuring safety. Recent research has revealed that refusal behavior can be mediated by a single direction in activation space, enabling targeted interventions to bypass…

Computation and Language · Computer Science 2026-02-26 Xinpeng Wang , Mingyang Wang , Yihong Liu , Hinrich Schütze , Barbara Plank

Language model inversion seeks to recover hidden prompts using only language model outputs. This capability has implications for security and accountability in language model deployments, such as leaking private information from an…

Computation and Language · Computer Science 2025-12-12 Murtaza Nazir , Matthew Finlayson , John X. Morris , Xiang Ren , Swabha Swayamdipta

Backdoor attacks pose severe security threats to large language models (LLMs), where a model behaves normally under benign inputs but produces malicious outputs when a hidden trigger appears. Existing backdoor removal methods typically…

Cryptography and Security · Computer Science 2026-03-17 Jianwei Li , Jung-Eun Kim

Large Language Models (LLMs) are widely integrated into interactive systems such as dialogue agents and task-oriented assistants. This growing ecosystem also raises supply-chain risks, where adversaries can distribute poisoned models that…

Cryptography and Security · Computer Science 2026-05-26 Yiyang Lu , Jinwen He , Yue Zhao , Kai Chen , Ruigang Liang , Cheng Hong , Yingjun Zhang

Large Language Models (LLMs) exhibit position bias systematically underweighting information based on its location in the context but how this bias varies across languages and models remains unclear. We conduct a multilingual study across…

Backdoor attacks pose a significant threat to Large Language Models (LLMs), where adversaries can embed hidden triggers to manipulate LLM's outputs. Most existing defense methods, primarily designed for classification tasks, are ineffective…

Cryptography and Security · Computer Science 2025-11-12 Zihan Wang , Rui Zhang , Hongwei Li , Wenshu Fan , Wenbo Jiang , Qingchuan Zhao , Guowen Xu

Large language models (LLMs) often exhibit undesirable behaviors, such as hallucinations and sequence repetitions. We propose to view these behaviors as fallbacks that models exhibit under epistemic uncertainty, and investigate the…

Computation and Language · Computer Science 2025-02-11 Maor Ivgi , Ori Yoran , Jonathan Berant , Mor Geva

We present a multilingual, continuous backchannel prediction model for Japanese, English, and Chinese, and use it to investigate cross-linguistic timing behavior. The model is Transformer-based and operates at the frame level, jointly…

Computation and Language · Computer Science 2025-12-17 Koji Inoue , Mikey Elmers , Yahui Fu , Zi Haur Pang , Taiga Mori , Divesh Lala , Keiko Ochi , Tatsuya Kawahara

Prompts have significantly improved the performance of pretrained Large Language Models (LLMs) on various downstream tasks recently, making them increasingly indispensable for a diverse range of LLM application scenarios. However, the…

Computation and Language · Computer Science 2023-12-19 Hongwei Yao , Jian Lou , Zhan Qin

Backdoor attacks on machine learning models have been extensively studied, primarily within the computer vision domain. Originally, these attacks manipulated classifiers to generate incorrect outputs in the presence of specific, often…

Machine Learning · Computer Science 2025-03-25 Sharon Lin , Krishnamurthy , Dvijotham , Jamie Hayes , Chongyang Shi , Ilia Shumailov , Shuang Song

Transferable backdoors pose a severe threat to the Pre-trained Language Models (PLMs) supply chain, yet defensive research remains nascent, primarily relying on detecting anomalies in the output feature space. We identify a critical flaw…

Cryptography and Security · Computer Science 2025-12-09 Tianhang Zhao , Wei Du , Haodong Zhao , Sufeng Duan , Gongshen Liu

While effective backdoor detection and inversion schemes have been developed for AIs used e.g. for images, there are challenges in "porting" these methods to LLMs. First, the LLM input space is discrete, which precludes gradient-based…

Machine Learning · Computer Science 2025-09-22 Zhengxing Li , Guangmingmei Yang , Jayaram Raghuram , David J. Miller , George Kesidis

The prompt-based learning paradigm, which bridges the gap between pre-training and fine-tuning, achieves state-of-the-art performance on several NLP tasks, particularly in few-shot settings. Despite being widely applied, prompt-based…

Computation and Language · Computer Science 2024-02-05 Shuai Zhao , Jinming Wen , Luu Anh Tuan , Junbo Zhao , Jie Fu
‹ Prev 1 3 4 5 6 7 10 Next ›