English
Related papers

Related papers: Self and Cross-Model Distillation for LLMs: Effect…

200 papers

The surge in Large Language Models (LLMs) has revolutionized natural language processing, but fine-tuning them for specific tasks often encounters challenges in balancing performance and preserving general instruction-following abilities.…

Computation and Language · Computer Science 2024-05-29 Zhaorui Yang , Tianyu Pang , Haozhe Feng , Han Wang , Wei Chen , Minfeng Zhu , Qian Liu

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

Large Language Models (LLMs), especially their compact efficiency-oriented variants, remain susceptible to jailbreak attacks that can elicit harmful outputs despite extensive alignment efforts. Existing adversarial prompt generation…

Large language models (LLMs) have demonstrated revolutionary capabilities in understanding complex contexts and performing a wide range of tasks. However, LLMs can also answer questions that are unethical or harmful, raising concerns about…

Cryptography and Security · Computer Science 2025-04-15 Kang Yang , Guanhong Tao , Xun Chen , Jun Xu

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing tasks. However, their enormous parameter size and extremely high requirements for compute power pose challenges for…

Computation and Language · Computer Science 2024-03-26 Bohao Yang , Chen Tang , Kun Zhao , Chenghao Xiao , Chenghua Lin

Deploying large language models (LLMs) is challenging because they are memory inefficient and compute-intensive for practical applications. In reaction, researchers train smaller task-specific models by either finetuning with human labels…

Computation and Language · Computer Science 2023-07-06 Cheng-Yu Hsieh , Chun-Liang Li , Chih-Kuan Yeh , Hootan Nakhost , Yasuhisa Fujii , Alexander Ratner , Ranjay Krishna , Chen-Yu Lee , Tomas Pfister

The rapid advancement of large language models (LLMs) has significantly advanced the capabilities of artificial intelligence across various domains. However, their massive scale and high computational costs render them unsuitable for direct…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Miao Rang , Zhenni Bi , Hang Zhou , Hanting Chen , An Xiao , Tianyu Guo , Kai Han , Xinghao Chen , Yunhe Wang

Mitigating the retention of sensitive or private information in large language models is essential for enhancing privacy and safety. Existing unlearning methods, like Gradient Ascent and Negative Preference Optimization, directly tune…

Computation and Language · Computer Science 2024-10-17 Yijiang River Dong , Hongzhou Lin , Mikhail Belkin , Ramon Huerta , Ivan Vulić

Safety-aligned large language models (LLMs) sometimes falsely refuse pseudo-harmful prompts, like "how to kill a mosquito," which are actually harmless. Frequent false refusals not only frustrate users but also provoke a public backlash…

Computation and Language · Computer Science 2025-06-12 Bang An , Sicheng Zhu , Ruiyi Zhang , Michael-Andrei Panaitescu-Liess , Yuancheng Xu , Furong Huang

Large language models (LLMs) have achieved remarkable advancements in natural language processing. However, the massive scale and computational demands of these models present formidable challenges when considering their practical…

Computation and Language · Computer Science 2024-04-09 Weize Liu , Guocong Li , Kai Zhang , Bang Du , Qiyuan Chen , Xuming Hu , Hongxia Xu , Jintai Chen , Jian Wu

As large language models (LLMs) increasingly mediate emotionally sensitive conversations, especially in mental health contexts, their ability to recognize and respond to high-risk situations becomes a matter of public safety. This study…

Large language models (LLMs) are vulnerable when trained on datasets containing harmful content, which leads to potential jailbreaking attacks in two scenarios: the integration of harmful texts within crowdsourced data used for pre-training…

Cryptography and Security · Computer Science 2024-06-03 Xiaoqun Liu , Jiacheng Liang , Muchao Ye , Zhaohan Xi

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse applications, yet they pose significant security risks that threaten their safe deployment in critical domains. Current security alignment methodologies…

Cryptography and Security · Computer Science 2025-07-22 Pengfei Du

Large Language Models (LLMs) are known to be susceptible to crafted adversarial attacks or jailbreaks that lead to the generation of objectionable content despite being aligned to human preferences using safety fine-tuning methods. While…

Computation and Language · Computer Science 2025-03-26 Sravanti Addepalli , Yerram Varun , Arun Suggala , Karthikeyan Shanmugam , Prateek Jain

Diffusion large language models (dLLMs) offer capabilities beyond those of autoregressive (AR) LLMs, such as parallel decoding and random-order generation. However, realizing these benefits in practice is non-trivial, as dLLMs inherently…

Machine Learning · Computer Science 2026-01-30 Yu-Yang Qian , Junda Su , Lanxiang Hu , Peiyuan Zhang , Zhijie Deng , Peng Zhao , Hao Zhang

Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…

Computation and Language · Computer Science 2025-06-24 Laurène Vaugrante , Francesca Carlon , Maluna Menke , Thilo Hagendorff

In this paper, we investigate how model distillation impacts the development of reasoning features in large language models (LLMs). To explore this, we train a crosscoder on Qwen-series models and their fine-tuned variants. Our results…

Machine Learning · Computer Science 2025-03-26 David D. Baek , Max Tegmark

Aligning large language models (LLMs) with human expectations without human-annotated preference data is an important problem. In this paper, we propose a method to evaluate the response preference by using the output probabilities of…

Computation and Language · Computer Science 2024-08-16 Aiwei Liu , Haoping Bai , Zhiyun Lu , Xiang Kong , Simon Wang , Jiulong Shan , Meng Cao , Lijie Wen

The distillation of knowledge from Large Language Models (LLMs) into Smaller Language Models (SLMs), preserving the capabilities and performance of LLMs while reducing model size, has played a key role in the proliferation of LLMs. Because…

Computation and Language · Computer Science 2025-07-14 Henry J. Xie , Jinghan Zhang , Xinhao Zhang , Kunpeng Liu

Large Language Models (LLMs) are widely used across sectors, yet their alignment with International Humanitarian Law (IHL) is not well understood. This study evaluates eight leading LLMs on their ability to refuse prompts that explicitly…

Computers and Society · Computer Science 2025-06-10 John Mavi , Diana Teodora Găitan , Sergio Coronado