English
Related papers

Related papers: Please refuse to answer me! Mitigating Over-Refusa…

200 papers

Large language models (LLMs) tend to inadequately integrate input context during text generation, relying excessively on encoded prior knowledge in model parameters, potentially resulting in generated text with factual inconsistencies or…

Computation and Language · Computer Science 2024-05-07 Zheng Zhao , Emilio Monti , Jens Lehmann , Haytham Assem

The development of LLMs has greatly enhanced the intelligence and fluency of question answering, while the emergence of retrieval enhancement has enabled models to better utilize external information. However, the presence of noise and…

Computation and Language · Computer Science 2024-09-19 Xingyun Hong , Yan Shao , Zhilin Wang , Manni Duan , Jin Xiongnan

Large Language Models (LLMs) are trained to refuse harmful requests, yet they remain vulnerable to jailbreak attacks that exploit weaknesses in conversational safety mechanisms. We introduce Incremental Completion Decomposition (ICD), a…

Computation and Language · Computer Science 2026-04-30 Samee Arif , Naihao Deng , Zhijing Jin , Rada Mihalcea

Despite extensive efforts in safety alignment, large language models (LLMs) remain vulnerable to jailbreak attacks. Activation steering offers a training-free defense method but relies on fixed steering coefficients, resulting in suboptimal…

Cryptography and Security · Computer Science 2025-09-22 Weixiang Zhao , Jiahe Guo , Yulin Hu , Yang Deng , An Zhang , Xingyu Sui , Xinyang Han , Yanyan Zhao , Bing Qin , Tat-Seng Chua , Ting Liu

In this paper, we investigate the degree to which fine-tuning in Large Language Models (LLMs) effectively mitigates versus merely conceals undesirable behavior. Through the lens of semi-realistic role-playing exercises designed to elicit…

Computation and Language · Computer Science 2024-07-01 Florin Pop , Judd Rosenblatt , Diogo Schwerz de Lucena , Michael Vaiana

Diffusion language models (DLMs) have recently emerged as a strong alternative to autoregressive models by enabling parallel text generation. To improve inference efficiency and KV-cache compatibility, prior work commonly adopts block-based…

Computation and Language · Computer Science 2026-01-21 Yingte Shu , Yuchuan Tian , Chao Xu , Yunhe Wang , Hanting Chen

Large Language Models (LLMs) have demonstrated remarkable capabilities but often face challenges with tasks requiring sophisticated reasoning. While Chain-of-Thought (CoT) prompting significantly enhances reasoning, it indiscriminately…

Machine Learning · Computer Science 2025-05-27 Chenwei Lou , Zewei Sun , Xinnian Liang , Meng Qu , Wei Shen , Wenqi Wang , Yuntao Li , Qingping Yang , Shuangzhi Wu

With the rapid evolution of Large Language Models (LLMs) and their large-scale experimentation in cloud-computing spaces, the challenge of guaranteeing their security and efficiency in a failure scenario has become a main issue. To ensure…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-03-18 Yihong Jin , Ze Yang , Xinhe Xu , Yihan Zhang , Shuyang Ji

Mitigating hallucinations in Large Language Models (LLMs) is critical for their reliable deployment. Existing methods typically fine-tune LLMs to abstain from answering questions beyond their knowledge scope. However, these methods often…

Computation and Language · Computer Science 2025-10-29 Hao An , Yang Xu

To circumvent the alignment of large language models (LLMs), current optimization-based adversarial attacks usually craft adversarial prompts by maximizing the likelihood of a so-called affirmative response. An affirmative response is a…

While large vision-language models (LVLMs) have shown impressive capabilities in generating plausible responses correlated with input visual contents, they still suffer from hallucinations, where the generated text inaccurately reflects…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Yi-Lun Lee , Yi-Hsuan Tsai , Wei-Chen Chiu

Large Language Models (LLMs) have become an indispensable part of natural language processing tasks. However, autoregressive sampling has become an efficiency bottleneck. Multi-Draft Speculative Decoding (MDSD) is a recent approach where,…

Computation and Language · Computer Science 2025-02-27 Zhengmian Hu , Tong Zheng , Vignesh Viswanathan , Ziyi Chen , Ryan A. Rossi , Yihan Wu , Dinesh Manocha , Heng Huang

Speculative Decoding is a prominent technique for accelerating the autoregressive inference of large language models (LLMs) by employing a fast draft model to propose candidate token sequences and a large target model to verify them in…

Computation and Language · Computer Science 2025-12-18 Chendong Sun , Ali Mao , Lei Xu , mingmin Chen

Diffusion large language models (dLLMs) enable any-order generation, but this flexibility enlarges the attack surface: harmful spans may appear at arbitrary positions, and template-based prefilling attacks such as DIJA bypass response-level…

Computation and Language · Computer Science 2026-02-04 Wonje Jeung , Sangyeon Yoon , Yoonjun Cho , Dongjae Jeon , Sangwoo Shin , Hyesoo Hong , Albert No

The training data in large language models is key to their success, but it also presents privacy and security risks, as it may contain sensitive information. Detecting pre-training data is crucial for mitigating these concerns. Existing…

Computation and Language · Computer Science 2025-01-16 Cheng Wang , Yiwei Wang , Bryan Hooi , Yujun Cai , Nanyun Peng , Kai-Wei Chang

We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches encode refusal behaviors across multiple latent features, suppressing a single dominant…

Machine Learning · Computer Science 2026-02-20 Zachary Coalson , Beth Sohler , Aiden Gabriel , Sanghyun Hong

For Large Language Models (LLMs) to be reliably deployed, models must effectively know when not to answer: abstain. Reasoning models, in particular, have gained attention for impressive performance on complex tasks. However, reasoning…

Artificial Intelligence · Computer Science 2026-04-03 Abinitha Gourabathina , Inkit Padhi , Manish Nagireddy , Subhajit Chaudhury , Prasanna Sattigeri

Diffusion Large Language Models (DLLMs) promise fast non-autoregressive inference but suffer a severe quality-speed trade-off in parallel decoding. This stems from the ''combinatorial contradiction'' phenomenon, where parallel tokens form…

Computation and Language · Computer Science 2026-02-27 Yushi Ye , Feng Hong , Huangjie Zheng , Xu Chen , Zhiyong Chen , Yanfeng Wang , Jiangchao Yao

Large reasoning models (LRMs) achieve impressive reasoning capabilities by generating lengthy chain-of-thoughts, but this "overthinking" incurs high latency and cost without commensurate accuracy gains. In this work, we introduce AALC, a…

Computation and Language · Computer Science 2025-08-11 Ruosen Li , Ziming Luo , Quan Zhang , Ruochen Li , Ben Zhou , Ali Payani , Xinya Du

Despite the substantial advancements in artificial intelligence, large language models (LLMs) remain being challenged by generation safety. With adversarial jailbreaking prompts, one can effortlessly induce LLMs to output harmful content,…

Computation and Language · Computer Science 2025-02-18 Yuhao Du , Zhuo Li , Pengyu Cheng , Xiang Wan , Anningzhe Gao