English
Related papers

Related papers: Model Merging and Safety Alignment: One Bad Model …

200 papers

Safety alignment is crucial to ensure that large language models (LLMs) behave in ways that align with human preferences and prevent harmful actions during inference. However, recent studies show that the alignment can be easily compromised…

Machine Learning · Computer Science 2024-11-01 ShengYun Peng , Pin-Yu Chen , Matthew Hull , Duen Horng Chau

Fine-tuning large language models (LMs) for individual tasks yields strong performance but is expensive for deployment and storage. Recent works explore model merging to combine multiple task-specific models into a single multi-task model…

Computation and Language · Computer Science 2025-05-30 Haobo Zhang , Jiayu Zhou

Models trained on different datasets can be merged by a weighted-averaging of their parameters, but why does it work and when can it fail? Here, we connect the inaccuracy of weighted-averaging to mismatches in the gradients and propose a…

Machine Learning · Computer Science 2024-08-26 Nico Daheim , Thomas Möllenhoff , Edoardo Maria Ponti , Iryna Gurevych , Mohammad Emtiyaz Khan

Despite the remarkable capabilities of Language Models (LMs) across diverse tasks, no single model consistently outperforms others, necessitating efficient methods to combine their strengths without expensive retraining. Existing model…

Computation and Language · Computer Science 2025-05-27 Jian Gu , Aldeida Aleti , Chunyang Chen , Hongyu Zhang

Model editing techniques are essential for efficiently updating knowledge in large language models (LLMs). However, the effectiveness of existing approaches degrades in massive editing scenarios, particularly when evaluated with practical…

Computation and Language · Computer Science 2026-02-25 Yanbo Dai , Zhenlan Ji , Zongjie Li , Shuai Wang

Merging has become a widespread way to cheaply combine individual models into a single model that inherits their capabilities and attains better performance. This popularity has spurred rapid development of many new merging methods, which…

Machine Learning · Computer Science 2024-09-30 Derek Tam , Yash Kant , Brian Lester , Igor Gilitschenski , Colin Raffel

Large language models (LLMs) are known to inherit and even amplify societal biases present in their pre-training corpora, threatening fairness and social trust. To address this issue, recent work has explored ``editing'' LLM parameters to…

Computation and Language · Computer Science 2025-12-03 Daiki Shirafuji , Tatsuhiko Saito , Yasutomo Kimura

Large language models (LLMs) have transformed many fields, including natural language processing, computer vision, and reinforcement learning. These models have also made a significant impact in the field of law, where they are being…

Computation and Language · Computer Science 2023-03-17 Zhongxiang Sun

While large language models demonstrate remarkable capabilities at task-specific applications through fine-tuning, extending these benefits across diverse languages is essential for broad accessibility. However, effective cross-lingual…

Computation and Language · Computer Science 2025-06-03 Danni Liu , Jan Niehues

General purpose language models (LMs) encounter difficulties when processing domain-specific jargon and terminology, which are frequently utilized in specialized fields such as medicine or industrial settings. Moreover, they often find it…

Computation and Language · Computer Science 2023-11-02 Daniel Eitan , Menachem Pirchi , Neta Glazer , Shai Meital , Gil Ayach , Gidon Krendel , Aviv Shamsian , Aviv Navon , Gil Hetz , Joseph Keshet

Alignment of Large Language Models (LLMs) remains an unsolved problem. Human preferences are highly distributed and can be captured at multiple levels of abstraction, from the individual to diverse populations. Organisational preferences,…

Machine Learning · Computer Science 2024-08-02 Gareth Seneque , Lap-Hang Ho , Ariel Kuperman , Nafise Erfanian Saeedi , Jeffrey Molendijk

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their transition to real-world applications reveals a critical limitation: the inability to adapt to individual preferences while maintaining alignment with…

Computation and Language · Computer Science 2025-05-06 Jian Guan , Junfei Wu , Jia-Nan Li , Chuanqi Cheng , Wei Wu

Large Language Models (LLMs) deliver powerful AI capabilities but face deployment challenges due to high resource costs and latency, whereas Small Language Models (SLMs) offer efficiency and deployability at the cost of reduced performance.…

Artificial Intelligence · Computer Science 2025-05-13 Yi Chen , JiaHao Zhao , HaoHao Han

Multimodal Large Language Models (MLLMs) have achieved success across various domains. However, their applicability tends to degrade when confronted with different types of data inputs, especially for MLLMs that have been fine-tuned for…

Computation and Language · Computer Science 2025-07-02 Yang Dai , Jianxiang An , Tianwei Lin , Hongyang He , Hongzhe Huang , Wenqiao Zhang , Zheqi Lv , Siliang Tang , Yueting Zhuang

Large language models (LLMs) excel in diverse applications but face dual challenges: generating harmful content under jailbreak attacks and over-refusal of benign queries due to rigid safety mechanisms. These issues are further complicated…

Artificial Intelligence · Computer Science 2025-11-04 Yifan Xia , Guorui Chen , Wenqian Yu , Zhijiang Li , Philip Torr , Jindong Gu

Mixing datasets for fine-tuning large models (LMs) has become critical for maximizing performance on downstream tasks. However, composing effective dataset mixtures typically relies on heuristics and trial-and-error, often requiring…

Machine Learning · Computer Science 2025-05-23 Zhixu Silvia Tao , Kasper Vinken , Hao-Wei Yeh , Avi Cooper , Xavier Boix

Recent advances in Multimodal Large Language Models (MLLMs) have enhanced their versatility as they integrate a growing number of modalities. Considering the heavy cost of training MLLMs, it is efficient to reuse the existing ones and…

Machine Learning · Computer Science 2025-10-23 Dingkun Zhang , Shuhan Qi , Xinyu Xiao , Kehai Chen , Xuan Wang

Inspired by the exceptional general intelligence of Large Language Models (LLMs), researchers have begun to explore their application in pioneering the next generation of recommender systems - systems that are conversational, explainable,…

Information Retrieval · Computer Science 2024-08-06 Wensheng Lu , Jianxun Lian , Wei Zhang , Guanghua Li , Mingyang Zhou , Hao Liao , Xing Xie

Transfer learning - i.e., further fine-tuning a pre-trained model on a downstream task - can confer significant advantages, including improved downstream performance, faster convergence, and better sample efficiency. These advantages have…

Machine Learning · Computer Science 2023-10-30 Prateek Yadav , Derek Tam , Leshem Choshen , Colin Raffel , Mohit Bansal

The application scope of Large Language Models (LLMs) continues to expand, leading to increasing interest in personalized LLMs that align with human values. However, aligning these models with individual values raises significant safety…

Computation and Language · Computer Science 2025-06-10 Sooyung Choi , Jaehyeok Lee , Xiaoyuan Yi , Jing Yao , Xing Xie , JinYeong Bak