English
Related papers

Related papers: Subspace Control: Turning Constrained Model Steeri…

200 papers

With the prevalence of pre-training-fine-tuning paradigm, how to efficiently adapt the pre-trained model to the downstream tasks has been an intriguing issue. Parameter-Efficient Fine-Tuning (PEFT) methods have been proposed for low-cost…

Machine Learning · Computer Science 2024-06-11 Weixi Song , Zuchao Li , Lefei Zhang , Hai Zhao , Bo Du

Supervised Fine-Tuning (SFT) is a critical step for enhancing the instruction-following capabilities of Large Language Models (LLMs) and adapting them to specialized domains. However, SFT often leads to a degradation of the model's general…

Computation and Language · Computer Science 2025-07-01 Fei Ding , Baiqiao Wang

Large language models (LLMs) consistently benefit from further fine-tuning on various tasks. However, we observe that directly tuning the Instruct (i.e., instruction-tuned) models often leads to marginal improvements and even performance…

Computation and Language · Computer Science 2025-09-29 Taiqiang Wu , Runming Yang , Jiayi Li , Pengfei Hu , Yik-Chung Wu , Ngai Wong , Yujiu Yang

Unsupervised pre-training is now the predominant approach for both text and speech understanding. Self-attention models pre-trained on large amounts of unannotated data have been hugely successful when fine-tuned on downstream tasks from a…

Computation and Language · Computer Science 2021-10-22 Ankur Bapna , Yu-an Chung , Nan Wu , Anmol Gulati , Ye Jia , Jonathan H. Clark , Melvin Johnson , Jason Riesa , Alexis Conneau , Yu Zhang

Supervised fine-tuning (SFT) is a standard approach to adapting large language models (LLMs) to new domains. In this work, we improve the statistical efficiency of SFT by selecting an informative subset of training examples. Specifically,…

Machine Learning · Computer Science 2025-05-22 Rohan Deb , Kiran Thekumparampil , Kousha Kalantari , Gaurush Hiranandani , Shoham Sabach , Branislav Kveton

Supervised fine-tuning (SFT) plays a crucial role in adapting large language models (LLMs) to specific domains or tasks. However, as demonstrated by empirical experiments, the collected data inevitably contains noise in practical…

Computation and Language · Computer Science 2024-12-20 Junyu Luo , Xiao Luo , Kaize Ding , Jingyang Yuan , Zhiping Xiao , Ming Zhang

Instruction tuning in multimodal large language models (MLLMs) generally involves cooperative learning between a backbone LLM and a feature encoder of non-text input modalities. The major challenge is how to efficiently find the synergy…

Machine Learning · Computer Science 2025-09-10 Xintong Li , Junda Wu , Tong Yu , Yu Wang , Xiang Chen , Jiuxiang Gu , Lina Yao , Julian McAuley , Jingbo Shang

Supervised fine-tuning (SFT) of large language models can be viewed as an off-policy learning problem, where expert demonstrations come from a fixed behavior policy while training aims to optimize a target policy. Importance sampling is the…

Machine Learning · Computer Science 2025-09-22 Shiwan Zhao , Xuyang Zhao , Jiaming Zhou , Aobo Kong , Qicheng Li , Yong Qin

Vision-language models (VLMs) have demonstrated exceptional generalization capabilities for downstream tasks. Due to its efficiency, prompt learning has gradually become a more effective and efficient method for transferring VLMs to…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Chenhao Ding , Xinyuan Gao , Songlin Dong , Jizhou Han , Qiang Wang , Zhengdong Zhou , Yuhang He , Yihong Gong

Long-tailed semi-supervised learning (LTSSL) presents a formidable challenge where models must overcome the scarcity of tail samples while mitigating the noise from unreliable pseudo-labels. Most prior LTSSL methods are designed to train…

Machine Learning · Computer Science 2026-04-09 Zhiyuan Huang , Jiahao Chen , Bing Su

As AI systems become more capable of complex agentic tasks, they also become more capable of pursuing undesirable objectives and causing harm. Previous work has attempted to catch these unsafe instances by interrogating models directly…

Artificial Intelligence · Computer Science 2026-03-24 Chloe Li , Mary Phuong , Daniel Tan

Model steering represents a powerful technique that dynamically aligns large language models (LLMs) with human preferences during inference. However, conventional model-steering methods rely heavily on externally annotated data, not only…

Computation and Language · Computer Science 2025-07-15 Rongyi Zhu , Yuhui Wang , Tanqiu Jiang , Jiacheng Liang , Ting Wang

Automatic code generation has been a longstanding research topic. With the advancement of general-purpose large language models (LLMs), the ability to code stands out as one important measure to the model's reasoning performance. Usually, a…

Software Engineering · Computer Science 2024-12-18 Jie Chen , Xintian Han , Yu Ma , Xun Zhou , Liang Xiang

Model merging combines the parameters of multiple neural networks into a single model without additional training. As fine-tuned large language models (LLMs) proliferate, merging offers a computationally efficient alternative to ensembles…

Computation and Language · Computer Science 2026-03-31 Mingyang Song , Mao Zheng

Ensuring constraint satisfaction is a key requirement for safety-critical systems, which include most robotic platforms. For example, constraints can be used for modeling joint position/velocity/torque limits and collision avoidance.…

Robotics · Computer Science 2025-09-04 Elias Fontanari , Gianni Lunardi , Matteo Saveriano , Andrea Del Prete

Pretrained language models (PLMs) trained on large-scale unlabeled corpus are typically fine-tuned on task-specific downstream datasets, which have produced state-of-the-art results on various NLP tasks. However, the data discrepancy issue…

Computation and Language · Computer Science 2022-03-23 Jiali Zeng , Yufan Jiang , Shuangzhi Wu , Yongjing Yin , Mu Li

Longitudinal NLP tasks require reasoning over temporally ordered text to detect persistence and change in human behavior and opinions. However, in-context learning with large language models struggles on tasks where models must integrate…

Computation and Language · Computer Science 2026-04-21 Iqra Ali , Talia Tseriotou , Mahmud Elahi Akhter , Yuxiang Zhou , Maria Liakata

Safety alignment in Large Language Models (LLMs) inherently presents a multi-objective optimization conflict, often accompanied by an unintended degradation of general capabilities. Existing mitigation strategies typically rely on global…

Machine Learning · Computer Science 2026-01-09 Wang Cai , Yilin Wen , Jinchang Hou , Du Su , Guoqiu Wang , Zhonghou Lv , Chenfu Bao , Yunfang Wu

Model merging is a flexible and computationally tractable approach to merge single-task checkpoints into a multi-task model. Prior work has solely focused on constrained multi-task settings where there is a one-to-one mapping between a…

Computer Vision and Pattern Recognition · Computer Science 2025-04-16 Juan Garcia Giraldo , Nikolaos Dimitriadis , Ke Wang , Pascal Frossard

Fine-tuning pretrained language models (LMs) without making any architectural changes has become a norm for learning various language downstream tasks. However, for non-language downstream tasks, a common practice is to employ task-specific…