English
Related papers

Related papers: Discovering Knowledge-Critical Subnetworks in Pret…

200 papers

Pre-trained language models (PLMs) contain vast amounts of factual knowledge, but how the knowledge is stored in the parameters remains unclear. This paper delves into the complex task of understanding how factual knowledge is stored in…

Computation and Language · Computer Science 2023-12-21 Yuheng Chen , Pengfei Cao , Yubo Chen , Kang Liu , Jun Zhao

In this paper, we investigate knowledge forgetting in large language models with a focus on its generalisation, ensuring that models forget not only specific training samples but also related implicit knowledge. To this end, we begin by…

Computation and Language · Computer Science 2025-10-10 Huazheng Wang , Yongcheng Jing , Haifeng Sun , Yingjie Wang , Jingyu Wang , Jianxin Liao , Dacheng Tao

We explore the use of large pretrained language models as few-shot semantic parsers. The goal in semantic parsing is to generate a structured meaning representation given a natural language input. However, language models are trained to…

Topic models are one of the compelling methods for discovering latent semantics in a document collection. However, it assumes that a document has sufficient co-occurrence information to be effective. However, in short texts, co-occurrence…

Computation and Language · Computer Science 2023-10-25 Pritom Saha Akash , Jie Huang , Kevin Chen-Chuan Chang

Large pre-trained language models have demonstrated their proficiency in storing factual knowledge within their parameters and achieving remarkable results when fine-tuned for downstream natural language processing tasks. Nonetheless, their…

Computation and Language · Computer Science 2023-09-29 Konstantinos Andriopoulos , Johan Pouwelse

Neural language models (LMs) are typically trained using only lexical features, such as surface forms of words. In this paper, we argue this deprives the LM of crucial syntactic signals that can be detected at high confidence using existing…

Computation and Language · Computer Science 2018-03-13 Duncan Blythe , Alan Akbik , Roland Vollgraf

While vector-based language representations from pretrained language models have set a new standard for many NLP tasks, there is not yet a complete accounting of their inner workings. In particular, it is not entirely clear what aspects of…

Computation and Language · Computer Science 2021-04-16 Matteo Alleman , Jonathan Mamou , Miguel A Del Rio , Hanlin Tang , Yoon Kim , SueYeon Chung

Large language models (LLMs) serve as giant information stores, often including personal or copyrighted data, and retraining them from scratch is not a viable option. This has led to the development of various fast, approximate unlearning…

Computation and Language · Computer Science 2024-10-18 Minseok Choi , ChaeHun Park , Dohyun Lee , Jaegul Choo

Knowledge extraction is used to convert neural networks into symbolic descriptions with the objective of producing more comprehensible learning models. The central challenge is to find an explanation which is more comprehensible than the…

Artificial Intelligence · Computer Science 2020-03-23 Simon Odense , Artur d'Avila Garcez

As large language models (LLMs) are applied across diverse domains, the ability to selectively unlearn specific information is becoming increasingly essential. For instance, LLMs are expected to selectively provide confidential information…

Computation and Language · Computer Science 2025-06-04 Shota Takashiro , Takeshi Kojima , Andrew Gambardella , Qi Cao , Yusuke Iwasawa , Yutaka Matsuo

While transferring a pretrained language model, common approaches conventionally attach their task-specific classifiers to the top layer and adapt all the pretrained layers. We investigate whether one could make a task-specific selection on…

Computation and Language · Computer Science 2022-10-20 Shuo Xie , Jiahao Qiu , Ankita Pasad , Li Du , Qing Qu , Hongyuan Mei

Extracting structured knowledge from texts has traditionally been used for knowledge base generation. However, other sources of information, such as images can be leveraged into this process to build more complete and richer knowledge…

Computer Vision and Pattern Recognition · Computer Science 2020-09-15 Ashutosh Tiwari , Sandeep Varma

Large-scale vision-language models (VLMs) exhibit remarkable zero-shot capabilities, yet the internal mechanisms driving their anomaly detection (AD) performance remain poorly understood. Current methods predominantly treat VLMs as…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Shaotian Li , Shangze Li , Chuancheng Shi , Wenhua Wu , Yanqiu Wu , Xiaohan Yu , Fei Shen , Tat-Seng Chua

Pre-trained language models have been found to capture a surprisingly rich amount of lexical knowledge, ranging from commonsense properties of everyday concepts to detailed factual knowledge about named entities. Among others, this makes it…

Computation and Language · Computer Science 2022-09-12 Asahi Ushio , Jose Camacho-Collados , Steven Schockaert

English pretrained language models, which make up the backbone of many modern NLP systems, require huge amounts of unlabeled training data. These models are generally presented as being trained only on English text but have been found to…

Computation and Language · Computer Science 2022-11-18 Terra Blevins , Luke Zettlemoyer

Large language models suffer from knowledge staleness and lack of interpretability due to implicit knowledge storage across entangled network parameters, preventing targeted updates and reasoning transparency. We propose ExplicitLM, a novel…

Artificial Intelligence · Computer Science 2025-11-04 Chengzhang Yu , Zening Lu , Chenyang Zheng , Chiyue Wang , Yiming Zhang , Zhanpeng Jin

Prior work has found that pretrained language models (LMs) fine-tuned with different random seeds can achieve similar in-domain performance but generalize differently on tests of syntactic generalization. In this work, we show that, even…

Computation and Language · Computer Science 2024-06-06 Adithya Bhaskar , Dan Friedman , Danqi Chen

We propose a subgraph importance estimation method for pretrained Graph Neural Networks (GNNs) on graph-level tasks, formulated as a linear Group Lasso regression problem in the embedding space. Our method effectively leverages prior domain…

Machine Learning · Computer Science 2026-05-13 Changhyun Kim , Seunghwan An , Jong-June Jeon

Interpretability benefits the theoretical understanding of representations. Existing word embeddings are generally dense representations. Hence, the meaning of latent dimensions is difficult to interpret. This makes word embeddings like a…

Computation and Language · Computer Science 2023-06-27 Minxue Xia , Hao Zhu

Machine unlearning in Vision-Language Models (VLMs) is typically performed at the image or instance level, making it difficult to precisely remove target knowledge without affecting unrelated semantics. This issue is especially pronounced…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Shen Lin , Jing Lin , Junhao Dong , Piotr Koniusz , Li Xu