English
Related papers

Related papers: GSS: Gated Subspace Steering for Selective Memoriz…

200 papers

Various Large Language Models~(LLMs) from the Generative Pretrained Transformer(GPT) family have achieved outstanding performances in a wide range of text generation tasks. However, the enormous model sizes have hindered their practical use…

Computation and Language · Computer Science 2024-04-24 Hang Shao , Bei Liu , Bo Xiao , Ke Zeng , Guanglu Wan , Yanmin Qian

Large language models (LLMs) often exhibit undesirable behaviors, such as safety violations and hallucinations. Although inference-time steering offers a cost-effective way to adjust model behavior without updating its parameters, existing…

Machine Learning · Computer Science 2026-04-20 Zixuan Weng , Jinghuai Zhang , Kunlin Cai , Ying Li , Peiran Wang , Yuan Tian

Large language model (LLM) training and finetuning are often bottlenecked by limited GPU memory. While existing projection-based optimization methods address this by projecting gradients into a lower-dimensional subspace to reduce optimizer…

Machine Learning · Computer Science 2024-06-26 Aashiq Muhamed , Oscar Li , David Woodruff , Mona Diab , Virginia Smith

Deploying large language models (LLMs) encounters challenges due to intensive computational and memory requirements. Our research examines vocabulary trimming (VT) inspired by restricting embedding entries to the language of interest to…

Computation and Language · Computer Science 2024-04-30 Nikolay Bogoychev , Pinzhen Chen , Barry Haddow , Alexandra Birch

Fine-tuning large language models (LLMs) is often constrained by the computational costs of processing massive datasets. We propose \textbf{QLESS} (Quantized Low-rank Gradient Similarity Search), which integrates gradient quantization with…

Generating structured textual content requires mechanisms that enforce coherence, stability, and adherence to predefined constraints while maintaining semantic fidelity. Conventional approaches often rely on rule-based heuristics or…

Computation and Language · Computer Science 2025-08-11 Derek Yotheringhay , Beatrix Nightingale , Maximilian Featherstone , Edmund Worthington , Hugo Ashdown

Learning a stable Linear Dynamical System (LDS) from data involves creating models that both minimize reconstruction error and enforce stability of the learned representation. We propose a novel algorithm for learning stable LDSs. Using a…

Machine Learning · Computer Science 2020-11-19 Giorgos Mamakoukas , Orest Xherija , T. D. Murphey

Multimodal large language models (MLLMs) have demonstrated remarkable potential for enhancing scene understanding in autonomous driving systems through powerful logical reasoning capabilities. However, the deployment of these models faces…

Computer Vision and Pattern Recognition · Computer Science 2024-09-18 Yunsheng Ma , Amr Abdelraouf , Rohit Gupta , Ziran Wang , Kyungtae Han

Large language models (LLMs) increasingly require mechanisms for continual adaptation without full retraining. However, sequential updates can lead to catastrophic forgetting, where new edits degrade previously acquired knowledge. This work…

Machine Learning · Computer Science 2025-10-21 William Hoy , Nurcin Celik

Large language models (LLMs) suffer from catastrophic forgetting during continual learning. Conventional rehearsal-based methods rely on previous training data to retain the model's ability, which may not be feasible in real-world…

Computation and Language · Computer Science 2024-05-28 Jianheng Huang , Leyang Cui , Ante Wang , Chengyi Yang , Xinting Liao , Linfeng Song , Junfeng Yao , Jinsong Su

Despite large language models (LLMs) have achieved impressive achievements across numerous tasks, supervised fine-tuning (SFT) remains essential for adapting these models to specialized domains. However, SFT for domain specialization can be…

Computation and Language · Computer Science 2025-11-13 Yibai Liu , Shihang Wang , Zeming Liu , Zheming Song , Junzhe Wang , Jingjing Liu , Qingjie Liu , Yunhong Wang

Despite significant progress in alignment, large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors. Activation steering techniques offer a promising inference-time intervention approach, but…

Machine Learning · Computer Science 2026-01-28 Quy-Anh Dang , Chris Ngo

Large Language Models have received significant attention due to their abilities to solve a wide range of complex tasks. However these models memorize a significant proportion of their training data, posing a serious threat when disclosed…

Cryptography and Security · Computer Science 2025-07-16 Jérémie Dentan , Davide Buscaldi , Aymen Shabou , Sonia Vanier

Existing low-rank adaptation (LoRA) methods face challenges on sparse large language models (LLMs) due to the inability to maintain sparsity. Recent works introduced methods that maintain sparsity by augmenting LoRA techniques with…

Computation and Language · Computer Science 2025-01-16 Yuxuan Hu , Jing Zhang , Xiaodong Chen , Zhe Zhao , Cuiping Li , Hong Chen

Fine-tuning large language models (LLMs) for specialized domains often necessitates a trade-off between acquiring domain expertise and retaining general reasoning capabilities, a phenomenon known as catastrophic forgetting. Existing…

Machine Learning · Computer Science 2026-02-09 Xiyang Zhang , Yuanhe Tian , Hongzhi Wang , Yan Song

Multimodal Large Language Models (MLLMs) have demonstrated outstanding performance across a variety of domains. However, training MLLMs is often inefficient, as much of the computation is redundant due to the long input sequences from…

Machine Learning · Computer Science 2026-05-19 Kean Shi , Liang Chen , Haozhe Zhao , Baobao Chang

Latent space steering methods provide a practical approach to controlling large language models by applying steering vectors to intermediate activations, guiding outputs toward desired behaviors while avoiding retraining. Despite their…

Machine Learning · Computer Science 2026-01-13 Shawn Im , Sharon Li

Despite the significant advancements in Large Vision-Language Models (LVLMs), their tendency to generate hallucinations undermines reliability and restricts broader practical deployment. Among the hallucination mitigation methods, feature…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Tiantian Dang , Chao Bi , Shufan Shen , Jinzhe Liu , Qingming Huang , Shuhui Wang

Automated optimization modeling via Large Language Models (LLMs) has emerged as a promising approach to assist complex human decision-making. While post-training has become a pivotal technique to enhance LLMs' capabilities in this domain,…

Machine Learning · Computer Science 2026-02-13 Weiting Liu , Han Wu , Yufei Kuang , Xiongwei Han , Tao Zhong , Jianfeng Feng , Wenlian Lu

The continual learning capability of large language models (LLMs) is crucial for advancing artificial general intelligence. However, continual fine-tuning LLMs across various domains often suffers from catastrophic forgetting, characterized…

Computation and Language · Computer Science 2025-08-07 Yunan Zhang , Shuoran Jiang , Mengchen Zhao , Yuefeng Li , Yang Fan , Xiangping Wu , Qingcai Chen