English
Related papers

Related papers: Guardrail Baselines for Unlearning in LLMs

200 papers

Prompting a pretrained language model with natural language patterns has been proved effective for natural language understanding (NLU). However, our preliminary study reveals that manual discrete prompts often lead to unstable performance…

Computation and Language · Computer Science 2023-10-26 Xiao Liu , Yanan Zheng , Zhengxiao Du , Ming Ding , Yujie Qian , Zhilin Yang , Jie Tang

Reinforcement learning (RL) has become a central post-training paradigm for large language models (LLMs), but its performance is highly sensitive to the quality of training problems. This sensitivity stems from the non-stationarity of RL:…

Machine Learning · Computer Science 2026-02-26 Ningyuan Yang , Weihua Du , Weiwei Sun , Sean Welleck , Yiming Yang

Guardrail models (a.k.a. safety checkers) are widely deployed to screen user inputs before they reach large language models (LLMs), serving as a primary defense against prompt injection attacks. Due to strict context constraints, these…

Cryptography and Security · Computer Science 2026-05-25 Yuanbo Zhou , Changjia Zhu , Junyu Wang , Xu He , Yan Zhai , Kun Sun , Mingkui Wei , Junjie Xiong

Pretrained Language Models (PLMs) have advanced Natural Language Processing (NLP) tasks significantly, but finetuning PLMs on low-resource datasets poses significant challenges such as instability and overfitting. Previous methods tackle…

Computation and Language · Computer Science 2024-03-20 Sai Ashish Somayajula , Youwei Liang , Abhishek Singh , Li Zhang , Pengtao Xie

Class-incremental learning (CIL) enables models to learn new classes progressively while preserving knowledge of previously learned ones. Recent advances in this field have shifted towards parameter-efficient fine-tuning techniques, with…

Computer Vision and Pattern Recognition · Computer Science 2025-08-13 Haoran Chen , Ping Wang , Zihan Zhou , Xu Zhang , Zuxuan Wu , Yu-Gang Jiang

Large language model (LLM) unlearning has demonstrated its essential role in removing privacy and copyright-related responses, crucial for their legal and safe applications. However, the pursuit of complete unlearning often comes with…

Machine Learning · Computer Science 2025-06-06 Yue Wang , Qizhou Wang , Feng Liu , Wei Huang , Yali Du , Xiaojiang Du , Bo Han

Pre-trained vision-language models are able to interpret visual concepts and language semantics. Prompt learning, a method of constructing prompts for text encoders or image encoders, elicits the potentials of pre-trained models and readily…

Computer Vision and Pattern Recognition · Computer Science 2025-02-21 Zhenhan Huang , Tejaswini Pedapati , Pin-Yu Chen , Jianxi Gao

This paper investigates supervised fine-tuning of large language models (LLMs) to improve their pedagogical alignment in computing education, addressing concerns that LLMs may hinder learning outcomes. The project utilised a proprietary…

Computation and Language · Computer Science 2024-11-05 Alexandra Vassar , Jake Renzella , Emily Ross , Andrew Taylor

Despite advances in Preference Alignment (PA) for Large Language Models (LLMs), mainstream methods like Reinforcement Learning with Human Feedback (RLHF) face notable challenges. These approaches require high-quality datasets of positive…

Machine Learning · Computer Science 2025-04-10 Xiaohua Feng , Yuyuan Li , Huwei Ji , Jiaming Zhang , Li Zhang , Tianyu Du , Chaochao Chen

The pretraining-fine-tuning paradigm has been the de facto strategy for transfer learning in modern language modeling. With the understanding that task adaptation in LMs is often a function of parameters shared across tasks, we argue that a…

Computation and Language · Computer Science 2024-06-24 Mandar Sharma , Nikhil Muralidhar , Shengzhe Xu , Raquib Bin Yousuf , Naren Ramakrishnan

In education, the capability of generating human-like text of Large Language Models (LLMs) inspired work on how they can increase the efficiency of learning and teaching. We study the affordability of these models for educators and students…

Computation and Language · Computer Science 2025-03-06 Bianca Raimondi , Saverio Giallorenzo , Maurizio Gabbrielli

Fine-tuning large language models (LLMs) for downstream tasks typically exhibit a fundamental safety-capability tradeoff, where improving task performance degrades safety alignment even on benign datasets. This degradation persists across…

While reinforcement learning (RL) has achieved notable success in various domains, training effective policies for complex tasks remains challenging. Agents often converge to local optima and fail to maximize long-term rewards. Existing…

Artificial Intelligence · Computer Science 2025-05-28 Heng Tan , Hua Yan , Yu Yang

In language modeling, neologisms are new tokens trained to represent a concept not already included in a given model's vocabulary. Neologisms can be used to encourage specific behavior in models, for example by appending prompts with "Give…

Computation and Language · Computer Science 2025-12-23 Sungjoon Park , Varun Ramamurthi , Owen Terry

The pretrain-finetune paradigm usually improves downstream performance over training a model from scratch on the same task, becoming commonplace across many areas of machine learning. While pretraining is empirically observed to be…

Computer Vision and Pattern Recognition · Computer Science 2023-07-13 Gabriele Merlin , Vedant Nanda , Ruchit Rawal , Mariya Toneva

Finetuning large pretrained neural networks is known to be resource-intensive, both in terms of memory and computational cost. To mitigate this, a common approach is to restrict training to a subset of the model parameters. By analyzing the…

Machine Learning · Computer Science 2025-10-23 Chao Zhou , Tom Jacobs , Advait Gadhikar , Rebekka Burkholz

Prompt-based learning paradigm bridges the gap between pre-training and fine-tuning, and works effectively under the few-shot setting. However, we find that this learning paradigm inherits the vulnerability from the pre-training stage,…

Computation and Language · Computer Science 2022-04-12 Lei Xu , Yangyi Chen , Ganqu Cui , Hongcheng Gao , Zhiyuan Liu

Large Language Models (LLMs) have found several use cases in education, ranging from automatic question generation to essay evaluation. In this paper, we explore the potential of using Large Language Models (LLMs) to author Intelligent…

Computation and Language · Computer Science 2024-04-26 Sankalan Pal Chowdhury , Vilém Zouhar , Mrinmaya Sachan

Human guidance in reinforcement learning (RL) is often impractical for large-scale applications due to high costs and time constraints. Large Language Models (LLMs) offer a promising alternative to mitigate RL sample inefficiency and…

Machine Learning · Computer Science 2024-11-25 Maryam Shoaeinaeini , Brent Harrison

Current literature demonstrates that Large Language Models (LLMs) are great few-shot learners, and prompting significantly increases their performance on a range of downstream tasks in a few-shot learning setting. An attempt to automate…

Computation and Language · Computer Science 2023-06-26 Yulin Zhou , Yiren Zhao , Ilia Shumailov , Robert Mullins , Yarin Gal