English
Related papers

Related papers: Do as I do (Safely): Mitigating Task-Specific Fine…

200 papers

When deployed in the real world, machine learning models inevitably encounter changes in the data distribution, and certain -- but not all -- distribution shifts could result in significant performance degradation. In practice, it may make…

Machine Learning · Statistics 2022-05-06 Aleksandr Podkopaev , Aaditya Ramdas

Instruction tuning enhances large language models (LLMs) to follow human instructions across diverse tasks, relying on high-quality datasets to guide behavior. However, these datasets, whether manually curated or synthetically generated,…

Language model-based instruction-following systems have lately shown increasing performance on many benchmark tasks, demonstrating the capability of adapting to a broad variety of instructions. However, such systems are often not designed…

Computation and Language · Computer Science 2024-03-20 Rahul Nadkarni , Yizhong Wang , Noah A. Smith

Loading models pre-trained on the large-scale corpus in the general domain and fine-tuning them on specific downstream tasks is gradually becoming a paradigm in Natural Language Processing. Previous investigations prove that introducing a…

Computation and Language · Computer Science 2021-09-15 Yao Qiu , Jinchao Zhang , Jie Zhou

Large language models (LLMs) may exhibit unintended or undesirable behaviors. Recent works have concentrated on aligning LLMs to mitigate harmful outputs. Despite these efforts, some anomalies indicate that even a well-conducted alignment…

Computation and Language · Computer Science 2025-09-24 Jiaming Ji , Kaile Wang , Tianyi Qiu , Boyuan Chen , Jiayi Zhou , Changye Li , Hantao Lou , Juntao Dai , Yunhuai Liu , Yaodong Yang

As the performance of larger, newer Large Language Models continues to improve for strategic Theory of Mind (ToM) tasks, the demand for these state-of-the-art models increases commensurately. However, their deployment is costly both in…

Computation and Language · Computer Science 2024-11-01 Nunzio Lore , Sepehr Ilami , Babak Heydari

The success of ChatGPT has recently attracted numerous efforts to replicate it, with instruction-tuning strategies being a key factor in achieving remarkable results. Instruction-tuning not only significantly enhances the model's…

Computation and Language · Computer Science 2023-03-28 Yunjie Ji , Yong Deng , Yan Gong , Yiping Peng , Qiang Niu , Lei Zhang , Baochang Ma , Xiangang Li

Following the initial flourishing of large language models (LLMs), there has been a surge in proposed large vision-language models (LVLMs) that integrate LLMs with vision capabilities. However, it has been observed that LVLMs, after tuning…

Computation and Language · Computer Science 2025-12-30 Daiki Shiono , Shumpei Miyawaki , Ryota Tanaka , Jun Suzuki

Large language models have the potential to generate explanations for their own predictions in a variety of styles based on user instructions. Recent research has examined whether these self-explanations faithfully reflect the models'…

Computation and Language · Computer Science 2025-12-09 Tomoki Doi , Masaru Isonuma , Hitomi Yanaka

Pre-training has achieved remarkable success when transferred to downstream tasks. In machine learning, we care about not only the good performance of a model but also its behavior under reasonable shifts of condition. The same philosophy…

Computer Vision and Pattern Recognition · Computer Science 2023-11-27 Jianghui Wang , Yang Chen , Xingyu Xie , Cong Fang , Zhouchen Lin

The desire to use reinforcement learning in safety-critical settings has inspired a recent interest in formal methods for learning algorithms. Existing formal methods for learning and optimization primarily consider the problem of…

Artificial Intelligence · Computer Science 2019-06-05 Nathan Fulton , Andre Platzer

Instruction tuning has been shown to be able to improve cross-task generalization of language models. However, it is still challenging for language models to complete the target tasks following the instructions, as the instructions are…

Computation and Language · Computer Science 2023-05-09 Yang Wu , Yanyan Zhao , Zhongyang Li , Bing Qin , Kai Xiong

Our decision-making processes are becoming more data driven, based on data from multiple sources, of different types, processed by a variety of technologies. As technology becomes more relevant for decision processes, the more likely they…

Computers and Society · Computer Science 2018-01-01 Tomasz Ostwald

Large language models (LLMs) exhibit remarkable capabilities in handling natural language tasks; however, they may struggle to consistently follow complex instructions including those involve multiple constraints. Post-training LLMs using…

Computation and Language · Computer Science 2025-05-20 Yuheng Lu , ZiMeng Bai , Caixia Yuan , Huixing Jiang , Xiaojie Wang

The deployment of large language models (LLMs) raises significant ethical and safety concerns. While LLM alignment techniques are adopted to improve model safety and trustworthiness, adversaries can exploit these techniques to undermine…

Cryptography and Security · Computer Science 2026-04-10 Rui Zhang , Hongwei Li , Yun Shen , Xinyue Shen , Wenbo Jiang , Guowen Xu , Yang Liu , Michael Backes , Yang Zhang

During training, reinforcement learning systems interact with the world without considering the safety of their actions. When deployed into the real world, such systems can be dangerous and cause harm to their surroundings. Often, dangerous…

Artificial Intelligence · Computer Science 2022-12-29 Ekaterina Nikonova , Cheng Xue , Jochen Renz

Recently introduced instruction-paradigm empowers non-expert users to leverage NLP resources by defining a new task in natural language. Instruction-tuned models have significantly outperformed multitask learning models (without…

Computation and Language · Computer Science 2023-02-15 Ravsehaj Singh Puri , Swaroop Mishra , Mihir Parmar , Chitta Baral

Harmful fine-tuning attack introduces significant security risks to the fine-tuning services. Main-stream defenses aim to vaccinate the model such that the later harmful fine-tuning attack is less effective. However, our evaluation results…

Computation and Language · Computer Science 2026-01-19 Yibo Wang , Tiansheng Huang , Li Shen , Huanjin Yao , Haotian Luo , Rui Liu , Naiqiang Tan , Jiaxing Huang , Dacheng Tao

AI model alignment is crucial due to inadvertent biases in training data and the underspecified machine learning pipeline, where models with excellent test metrics may not meet end-user requirements. While post-training alignment via human…

Machine Learning · Computer Science 2024-11-06 William Overman , Jacqueline Jil Vallon , Mohsen Bayati

Although large language models (LLMs) achieve effective safety alignment at the time of release, they still face various safety challenges. A key issue is that fine-tuning often compromises the safety alignment of LLMs. To address this…

Computation and Language · Computer Science 2025-05-27 Di Wu , Xin Lu , Yanyan Zhao , Bing Qin