English
Related papers

Related papers: Categorical Perception in Large Language Model Hid…

200 papers

We investigate the generalization properties of dense text embeddings when the embedding backbone is a large language model (LLM) versus when it is a non-LLM encoder, and we study the extent to which spherical linear interpolation (SLERP)…

Computation and Language · Computer Science 2025-12-01 Siyaxolisa Kabane

Machine learning (ML) models always make a prediction, even when they are likely to be wrong. This causes problems in practical applications, as we do not know if we should trust a prediction. ML with reject option addresses this issue by…

Multimodal large language models (MLLMs) perform strongly on natural images, yet their ability to understand discrete visual symbols remains unclear. We present a multi-domain benchmark spanning language, culture, mathematics, physics and…

Recent advances in Large Language Models (LLMs) have stimulated a surge of research aimed at extending their applications to the visual domain. While these models exhibit promise in generating abstract image captions and facilitating…

Computation and Language · Computer Science 2023-10-27 Geewook Kim , Hodong Lee , Daehee Kim , Haeji Jung , Sanghee Park , Yoonsik Kim , Sangdoo Yun , Taeho Kil , Bado Lee , Seunghyun Park

This work investigates how large language models (LLMs) internally represent emotion by analyzing the geometry of their hidden-state space. The paper identifies a low-dimensional emotional manifold and shows that emotional representations…

Computation and Language · Computer Science 2026-02-02 Benjamin Reichman , Adar Avsian , Larry Heck

This paper investigates contextual word representation models from the lens of similarity analysis. Given a collection of trained models, we measure the similarity of their internal representations and attention. Critically, these models…

Computation and Language · Computer Science 2020-05-05 John M. Wu , Yonatan Belinkov , Hassan Sajjad , Nadir Durrani , Fahim Dalvi , James Glass

While Large Language Models (LLMs) demonstrate increasingly sophisticated affective capabilities, the internal mechanisms by which they process complex emotions remain unclear. Existing interpretability approaches often treat models as…

Computation and Language · Computer Science 2026-04-23 Yitong Shou , Manhao Guan

Large Language Models (LLMs) exhibit various emergent abilities. Among these abilities, some might reveal the internal working mechanisms of models. In this paper, we uncover a novel emergent capability in models: the intrinsic ability to…

Computation and Language · Computer Science 2024-07-17 Junhao Chen , Shengding Hu , Zhiyuan Liu , Maosong Sun

Large language models (LLMs) have achieved remarkable success and demonstrated superior performance across various tasks, including natural language processing (NLP), weather forecasting, biological protein folding, text generation, and…

Artificial Intelligence · Computer Science 2025-12-09 Sarang Patil , Zeyong Zhang , Yiran Huang , Tengfei Ma , Mengjia Xu

Humans effortlessly identify objects by leveraging a rich understanding of the surrounding scene, including spatial relationships, material properties, and the co-occurrence of other objects. In contrast, most computational object…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Ciprian Constantinescu , Marius Leordeanu

We propose a general framework called Network Dissection for quantifying the interpretability of latent representations of CNNs by evaluating the alignment between individual hidden units and a set of semantic concepts. Given any CNN model,…

Computer Vision and Pattern Recognition · Computer Science 2017-04-20 David Bau , Bolei Zhou , Aditya Khosla , Aude Oliva , Antonio Torralba

Cognitive Diagnosis Models (CDMs) are a special family of discrete latent variable models that are widely used in modern educational, psychological, social and biological sciences. A key component of CDMs is a binary $Q$-matrix…

Methodology · Statistics 2025-01-08 Chenchen Ma , Gongjun Xu

Recent open-vocabulary detection methods aim to detect novel objects by distilling knowledge from vision-language models (VLMs) trained on a vast amount of image-text pairs. To improve the effectiveness of these methods, researchers have…

Computer Vision and Pattern Recognition · Computer Science 2023-03-24 Han-Cheol Cho , Won Young Jhoo , Wooyoung Kang , Byungseok Roh

Most machine learning-based image segmentation models produce pixel-wise confidence scores that represent the model's predicted probability for each class label at every pixel. While this information can be particularly valuable in…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Bruno Viti , Elias Karabelas , Martin Holler

When a language model asserts that "the capital of Australia is Sydney," does it know this is wrong? We characterize the geometry of correctness representations across 9 models from 5 architecture families. The structure is simple: the…

Machine Learning · Computer Science 2026-02-10 Seonglae Cho , Zekun Wu , Kleyton Da Costa , Adriano Koshiyama

This article investigates, within the field of neuropsychology of artificial intelligence, the process of categorical segmentation performed by language models. This process involves, across different neural layers, the creation of new…

Continual learning of pretrained vision-language models (VLMs) is prone to catastrophic forgetting, yet current approaches adapt to new tasks without explicitly preserving the cross-modal semantic geometry inherited from pretraining and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Chiyuan He , Zihuan Qiu , Fanman Meng , Runtong Zhang , Linfeng Xu , Qingbo Wu , Hongliang Li

Constraint Programming (CP) and Machine Learning (ML) face challenges in text generation due to CP's struggle with implementing "meaning'' and ML's difficulty with structural constraints. This paper proposes a solution by combining both…

Computation and Language · Computer Science 2024-09-26 Florian Régin , Elisabetta De Maria , Alexandre Bonlarron

Large Language Models (LLMs) are known to exhibit social, demographic, and gender biases, often as a consequence of the data on which they are trained. In this work, we adopt a mechanistic interpretability approach to analyze how such…

Computation and Language · Computer Science 2025-06-09 Bhavik Chandna , Zubair Bashir , Procheta Sen

This commentary extends the discussion by Parr et al. on memory and attention beyond individual cognitive systems. From the perspective of the Collective Predictive Coding (CPC) hypothesis -- a framework for understanding these faculties…

Neurons and Cognition · Quantitative Biology 2025-08-25 Tadahiro Taniguchi