English
Related papers

Related papers: Beyond Single Concept Vector: Modeling Concept Sub…

200 papers

Concept-bottleneck models (CBMs) are neural classifiers that compute predictions from high-level concepts extracted from the input. CBMs ensure stakeholders can understand the concepts -- and the predictions they entail -- by learning these…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Nicola Debole , Andrea Passerini , Stefano Teso , Andrea Pugnana , Emanuele Marconato

With the growing popularity of general-purpose Large Language Models (LLMs), comes a need for more global explanations of model behaviors. Concept-based explanations arise as a promising avenue for explaining high-level patterns learned by…

Artificial Intelligence · Computer Science 2024-10-07 Meng Li , Haoran Jin , Ruixuan Huang , Zhihao Xu , Defu Lian , Zijia Lin , Di Zhang , Xiting Wang

Knowledge representation is a key component to the success of all rule based systems including learning classifier systems (LCSs). This component brings insight into how to partition the problem space what in turn seeks prominent role in…

Neural and Evolutionary Computing · Computer Science 2015-06-15 Farzaneh Shoeleh , Mahshid Majd , Ali Hamzeh , Sattar Hashemi

As the cost of pretraining large language models grows, there is continued interest in strategies to improve learning efficiency during this core training stage. Motivated by cognitive development, where humans gradually build knowledge as…

Computation and Language · Computer Science 2026-02-10 Karanpartap Singh , Neil Band , Ehsan Adeli

This paper connects a vector-based composition model to a formal semantics, the Dependency-based Compositional Semantics (DCS). We show theoretical evidence that the vector compositions in our model conform to the logic of DCS.…

Computation and Language · Computer Science 2016-06-09 Ran Tian , Naoaki Okazaki , Kentaro Inui

To increase the trustworthiness of deep neural networks, it is critical to improve the understanding of how they make decisions. This paper introduces a novel unsupervised concept-based model for image classification, named Learnable…

Machine Learning · Computer Science 2025-06-04 Francesco De Santis , Philippe Bich , Gabriele Ciravegna , Pietro Barbiero , Danilo Giordano , Tania Cerquitelli

Deep vision models have achieved remarkable classification performance by leveraging a hierarchical architecture in which human-interpretable concepts emerge through the composition of individual neurons across layers. Given the distributed…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Dahee Kwon , Sehyun Lee , Jaesik Choi

Majority of the text modelling techniques yield only point-estimates of document embeddings and lack in capturing the uncertainty of the estimates. These uncertainties give a notion of how well the embeddings represent a document. We…

Computation and Language · Computer Science 2020-08-03 Santosh Kesiraju , Oldřich Plchot , Lukáš Burget , Suryakanth V Gangashetty

Large language models (LLMs) can memorize and reproduce training sequences verbatim -- a tendency that undermines both generalization and privacy. Existing mitigation methods apply interventions uniformly, degrading performance on the…

Machine Learning · Computer Science 2026-02-10 Xuanqi Zhang , Haoyang Shang , Xiaoxiao Li

Multimodal Large Language Models (MLLMs) have achieved remarkable success in open-vocabulary perceptual tasks, yet their ability to solve complex cognitive problems remains limited, especially when visual details are abstract and require…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Boyi Li , Yifan Shen , Yuanzhe Liu , Yifan Xu , Jiateng Liu , Xinzhuo Li , Zhengyuan Li , Jingyuan Zhu , Yunhan Zhong , Fangzhou Lan , Jianguo Cao , James M. Rehg , Heng Ji , Ismini Lourentzou , Xu Cao

Logical query answering over Knowledge Graphs (KGs) is a fundamental yet complex task. A promising approach to achieve this is to embed queries and entities jointly into the same embedding space. Research along this line suggests that using…

Information Retrieval · Computer Science 2024-03-29 Yuhan Wu , Yuanyuan Xu , Wenjie Zhang , Xiwei Xu , Ying Zhang

Transformer language models (LMs) have been shown to represent concepts as directions in the latent space of hidden activations. However, for any human-interpretable concept, how can we find its direction in the latent space? We present a…

Computation and Language · Computer Science 2024-04-02 David Chanin , Anthony Hunter , Oana-Maria Camburu

Vector space word representations are learned from distributional information of words in large corpora. Although such statistics are semantically informative, they disregard the valuable information that is contained in semantic lexicons…

Computation and Language · Computer Science 2015-03-24 Manaal Faruqui , Jesse Dodge , Sujay K. Jauhar , Chris Dyer , Eduard Hovy , Noah A. Smith

Do large language models (LLMs) represent concepts abstractly, i.e., independent of input format? We revisit Function Vectors (FVs), compact representations of in-context learning (ICL) tasks that causally drive task performance. Across…

Computation and Language · Computer Science 2026-02-27 Gustaw Opiełka , Hannes Rosenbusch , Claire E. Stevenson

In-context learning (ICL) in Large Language Models (LLMs) has emerged as a powerful new learning paradigm. However, its underlying mechanism is still not well understood. In particular, it is challenging to map it to the "standard" machine…

Computation and Language · Computer Science 2023-10-25 Roee Hendel , Mor Geva , Amir Globerson

Pre-trained large language models (LLMs) reflect the inherent social biases of their training corpus. Many methods have been proposed to mitigate this issue, but they often fail to debias or they sacrifice model accuracy. We use…

Computation and Language · Computer Science 2023-11-01 Li S. Yifei , Lyle Ungar , João Sedoc

Recently, word representation has been increasingly focused on for its excellent properties in representing the word semantics. Previous works mainly suffer from the problem of polysemy phenomenon. To address this problem, most of previous…

Computation and Language · Computer Science 2015-11-20 Xinchi Chen , Xipeng Qiu , Jingxiang Jiang , Xuanjing Huang

We introduce a Gaussian Prototype Layer for gradient-based prototype learning and demonstrate two novel network architectures for explainable segmentation one of which relies on region proposals. Both models are evaluated on agricultural…

Computer Vision and Pattern Recognition · Computer Science 2023-06-27 Michael Gerstenberger , Steffen Maaß , Peter Eisert , Sebastian Bosse

Several recently proposed methods aim to learn conceptual space representations from large text collections. These learned representations asso- ciate each object from a given domain of interest with a point in a high-dimensional Euclidean…

Artificial Intelligence · Computer Science 2018-05-07 Zied Bouraoui , Steven Schockaert

We show that singular value decomposition of the lm_head} weight matrix of a transformer-based large language model -- requiring only five lines of PyTorch and no model inference -- reveals interpretable semantic subspaces directly from the…

Machine Learning · Computer Science 2026-05-26 Hisashi Miyashita