English
Related papers

Related papers: On the Robustness of Knowledge Editing for Detoxif…

200 papers

Unlearning in large language models (LLMs) is critical for regulatory compliance and for building ethical generative AI systems that avoid producing private, toxic, illegal, or copyrighted content. Despite rapid progress, in this work, we…

Machine Learning · Computer Science 2026-05-29 Hadi Reisizadeh , Jiajun Ruan , Yiwei Chen , Soumyadeep Pal , Sijia Liu , Mingyi Hong

While post-training quantization is widely adopted for efficient deployment of large language models, the mechanisms underlying quantization robustness remain unclear. We conduct a comprehensive analysis of quantization degradation across…

Machine Learning · Computer Science 2026-02-02 Albert Catalan-Tatjer , Niccolò Ajroldi , Jonas Geiping

Large language models (LLMs) exhibit exceptional performance but pose inherent risks of generating toxic content, restricting their safe deployment. While traditional methods (e.g., alignment) adjust output preferences, they fail to…

Machine Learning · Computer Science 2026-01-13 Zenghao Duan , Zhiyi Yin , Zhichao Shi , Liang Pang , Shaoling Jing , Zihe Huang , Jiayi Wu , Yu Yan , Jingcheng Deng , Huawei Shen , Xueqi Cheng

Multimodal Knowledge Editing (MKE) extends traditional knowledge editing to settings involving both textual and visual modalities. However, existing MKE benchmarks primarily assess final answer correctness while neglecting the quality of…

Artificial Intelligence · Computer Science 2025-12-02 Li Yuan , Qingfei Huang , Bingshan Zhu , Yi Cai , Qingbao Huang , Changmeng Zheng , Zikun Deng , Tao Wang

Multi-hop Question Answering (MQA) under knowledge editing (KE) is a key challenge in Large Language Models (LLMs). While best-performing solutions in this domain use a plan and solve paradigm to split a question into sub-questions followed…

Computation and Language · Computer Science 2024-05-28 Keyuan Cheng , Muhammad Asif Ali , Shu Yang , Gang Lin , Yuxuan Zhai , Haoyang Fei , Ke Xu , Lu Yu , Lijie Hu , Di Wang

Knowledge distillation (KD) is an effective method for model compression and transferring knowledge between models. However, its effect on model's robustness against spurious correlations that degrade performance on out-of-distribution data…

Machine Learning · Computer Science 2025-10-31 Jiali Cheng , Chirag Agarwal , Hadi Amiri

Knowledge Distillation (KD) transfers knowledge from a large teacher model to a smaller student by aligning their predictive distributions. However, conventional KD formulations - typically based on Kullback-Leibler divergence - assume that…

Machine Learning · Computer Science 2026-02-05 Ondrej Tybl , Lukas Neumann

Pre-trained language models have been applied to various NLP tasks with considerable performance gains. However, the large model sizes, together with the long inference time, limit the deployment of such models in real-time applications.…

Computation and Language · Computer Science 2022-11-03 Haojie Pan , Chengyu Wang , Minghui Qiu , Yichang Zhang , Yaliang Li , Jun Huang

Data contamination undermines the validity of Large Language Model evaluation by enabling models to rely on memorized benchmark content rather than true generalization. While prior work has proposed contamination detection methods, these…

Computation and Language · Computer Science 2026-01-22 Chaymaa Abbas , Nour Shamaa , Mariette Awad

Previous approaches to robustness in natural language processing usually treat deviant input by relaxing grammatical constraints whenever a successful analysis cannot be provided by ``normal'' means. This schema implies, that error…

cmp-lg · Computer Science 2016-08-31 Wolfgang Menzel

Knowledge distillation (KD) is commonly deemed as an effective model compression technique in which a compact model (student) is trained under the supervision of a larger pretrained model or an ensemble of models (teacher). Various…

Machine Learning · Computer Science 2020-07-08 Fahad Sarfraz , Elahe Arani , Bahram Zonooz

Post-hoc unlearning has emerged as a practical mechanism for removing undesirable concepts from large text-to-image diffusion models. However, prior work primarily evaluates unlearning through erasure success; its impact on broader…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Arian Komaei Koma , Seyed Amir Kasaei , Ali Aghayari , AmirMahdi Sadeghzadeh , Mohammad Hossein Rohban

Knowledge Distillation (KD) is an effective framework for compressing deep learning models, realized by a student-teacher paradigm requiring small student networks to mimic the soft target generated by well-trained teachers. However, the…

Computer Vision and Pattern Recognition · Computer Science 2020-05-20 Yuang Liu , Wei Zhang , Jun Wang

Diffusion-based purification (DBP) has become a cornerstone defense against adversarial examples (AEs), regarded as robust due to its use of diffusion models (DMs) that project AEs onto the natural data manifold. We refute this core claim,…

Cryptography and Security · Computer Science 2026-02-11 Andre Kassis , Urs Hengartner , Yaoliang Yu

In the pursuit of developing Large Language Models (LLMs) that adhere to societal standards, it is imperative to detect the toxicity in the generated text. The majority of existing toxicity metrics rely on encoder models trained on specific…

Computation and Language · Computer Science 2024-11-15 Hyukhun Koh , Dohyung Kim , Minwoo Lee , Kyomin Jung

Large language models and deep learning models designed for code intelligence have revolutionized the software engineering field due to their ability to perform various code-related tasks. These models can process source code and software…

Software Engineering · Computer Science 2025-07-31 Ali Asgari , Milan de Koning , Pouria Derakhshanfar , Annibale Panichella

Leveraging shared learning through Massively Multilingual Models, state-of-the-art machine translation models are often able to adapt to the paucity of data for low-resource languages. However, this performance comes at the cost of…

Computation and Language · Computer Science 2022-11-10 Harshita Diddee , Sandipan Dandapat , Monojit Choudhury , Tanuja Ganu , Kalika Bali

Current research on the \textit{Decompose-Then-Verify} paradigm for evaluating the factuality of long-form text typically treats decomposition and verification in isolation, overlooking their interactions and potential misalignment. We find…

Computation and Language · Computer Science 2025-05-27 Yining Lu , Noah Ziems , Hy Dang , Meng Jiang

Although large language models (LLMs) have achieved significant success, their vulnerability to adversarial perturbations, including recent jailbreak attacks, has raised considerable concerns. However, the increasing size of these models…

Computation and Language · Computer Science 2024-04-19 Jiabao Ji , Bairu Hou , Zhen Zhang , Guanhua Zhang , Wenqi Fan , Qing Li , Yang Zhang , Gaowen Liu , Sijia Liu , Shiyu Chang

Large language models (LLMs) demonstrate strong performance across natural language processing tasks, yet undergo significant performance degradation when modified for deployment through quantization, pruning, or decoding strategy…

Computation and Language · Computer Science 2025-04-01 Ziyang Ma , Zuchao Li , Lefei Zhang , Gui-Song Xia , Bo Du , Liangpei Zhang , Dacheng Tao
‹ Prev 1 8 9 10 Next ›