English
Related papers

Related papers: Discovering Latent Concepts Learned in BERT

200 papers

In this paper we investigate the linguistic knowledge learned by a Neural Language Model (NLM) before and after a fine-tuning process and how this knowledge affects its predictions during several classification problems. We use a wide set…

Computation and Language · Computer Science 2024-02-27 Alessio Miaschi , Dominique Brunato , Felice Dell'Orletta , Giulia Venturi

Probing complex language models has recently revealed several insights into linguistic and semantic patterns found in the learned representations. In this article, we probe BERT specifically to understand and measure the relational…

Computation and Language · Computer Science 2021-09-09 Jonas Wallat , Jaspreet Singh , Avishek Anand

Interpreting the inner workings of deep learning models is crucial for establishing trust and ensuring model safety. Concept-based explanations have emerged as a superior approach that is more interpretable than feature attribution…

Machine Learning · Computer Science 2023-07-17 Mara Graziani , Laura O' Mahony , An-Phi Nguyen , Henning Müller , Vincent Andrearczyk

Probing complex language models has recently revealed several insights into linguistic and semantic patterns found in the learned representations. In this paper, we probe BERT specifically to understand and measure the relational knowledge…

Computation and Language · Computer Science 2021-09-09 Jonas Wallat , Jaspreet Singh , Avishek Anand

Deep neural networks are inherently opaque and challenging to interpret. Unlike hand-crafted feature-based models, we struggle to comprehend the concepts learned and how they interact within these models. This understanding is crucial not…

Computation and Language · Computer Science 2023-07-12 Shammur Absar Chowdhury , Nadir Durrani , Ahmed Ali

We propose a novel framework ConceptX, to analyze how latent concepts are encoded in representations learned within pre-trained language models. It uses clustering to discover the encoded concepts and explains them by aligning with a large…

Computation and Language · Computer Science 2022-06-28 Hassan Sajjad , Nadir Durrani , Fahim Dalvi , Firoj Alam , Abdul Rafae Khan , Jia Xu

While large language models like BERT demonstrate strong empirical performance on semantic tasks, whether this reflects true conceptual competence or surface-level statistical association remains unclear. I investigate whether BERT encodes…

Computation and Language · Computer Science 2025-06-16 Cole Gawin

Transfer learning from pre-trained neural language models towards downstream tasks has been a predominant theme in NLP recently. Several researchers have shown that deep NLP models learn non-trivial amount of linguistic knowledge, captured…

Computation and Language · Computer Science 2021-06-01 Nadir Durrani , Hassan Sajjad , Fahim Dalvi

Pre-trained language models (PLMs) have been prevailing in state-of-the-art methods for natural language processing, and knowledge-enhanced PLMs are further proposed to promote model performance in knowledge-intensive tasks. However,…

Computation and Language · Computer Science 2024-01-12 Xintao Wang , Zhouhong Gu , Jiaqing Liang , Dakuan Lu , Yanghua Xiao , Wei Wang

Large pre-trained language models help to achieve state of the art on a variety of natural language processing (NLP) tasks, nevertheless, they still suffer from forgetting when incrementally learning a sequence of tasks. To alleviate this…

Computation and Language · Computer Science 2023-03-03 Mingxu Tao , Yansong Feng , Dongyan Zhao

Large language models (LLMs) have shown remarkable performances across a wide range of tasks. However, the mechanisms by which these models encode tasks of varying complexities remain poorly understood. In this paper, we explore the…

Computation and Language · Computer Science 2025-02-06 Mingyu Jin , Qinkai Yu , Jingyuan Huang , Qingcheng Zeng , Zhenting Wang , Wenyue Hua , Haiyan Zhao , Kai Mei , Yanda Meng , Kaize Ding , Fan Yang , Mengnan Du , Yongfeng Zhang

We study the evolution of latent space in fine-tuned NLP models. Different from the commonly used probing-framework, we opt for an unsupervised method to analyze representations. More specifically, we discover latent concepts in the…

Computation and Language · Computer Science 2022-10-25 Nadir Durrani , Hassan Sajjad , Fahim Dalvi , Firoj Alam

Language models have become nearly ubiquitous in natural language processing applications achieving state-of-the-art results in many tasks including prosody. As the model design does not define predetermined linguistic targets during…

Computation and Language · Computer Science 2023-04-26 Sofoklis Kakouros , Johannah O'Mahony

Learning concepts from natural high-dimensional data (e.g., images) holds potential in building human-aligned and interpretable machine learning models. Despite its encouraging prospect, formalization and theoretical insights into this…

Machine Learning · Computer Science 2025-01-16 Lingjing Kong , Guangyi Chen , Biwei Huang , Eric P. Xing , Yuejie Chi , Kun Zhang

When large language models (LLMs) use in-context learning (ICL) to solve a new task, they must infer latent concepts from demonstration examples. This raises the question of whether and how transformers represent latent structures as part…

Machine Learning · Computer Science 2025-09-29 Guan Zhe Hong , Bhavya Vasudeva , Vatsal Sharan , Cyrus Rashtchian , Prabhakar Raghavan , Rina Panigrahy

Recent breakthroughs of pretrained language models have shown the effectiveness of self-supervised learning for a wide range of natural language processing (NLP) tasks. In addition to standard syntactic and semantic NLP tasks, pretrained…

Computation and Language · Computer Science 2019-12-23 Wenhan Xiong , Jingfei Du , William Yang Wang , Veselin Stoyanov

One of the most remarkable properties of word embeddings is the fact that they capture certain types of semantic and syntactic relationships. Recently, pre-trained language models such as BERT have achieved groundbreaking results across a…

Computation and Language · Computer Science 2019-12-02 Zied Bouraoui , Jose Camacho-Collados , Steven Schockaert

Human beings primarily understand the world through concepts (e.g., dog), abstract mental representations that structure perception, reasoning, and learning. However, how large language models (LLMs) acquire, retain, and forget such…

Computation and Language · Computer Science 2026-01-08 Barry Menglong Yao , Sha Li , Yunzhi Yao , Minqian Liu , Zaishuo Xia , Qifan Wang , Lifu Huang

Heavily pre-trained transformer models such as BERT have recently shown to be remarkably powerful at language modelling by achieving impressive results on numerous downstream tasks. It has also been shown that they are able to implicitly…

Information Retrieval · Computer Science 2021-03-05 Gustavo Penha , Claudia Hauff

Previous studies investigating the syntactic abilities of deep learning models have not targeted the relationship between the strength of the grammatical generalization and the amount of evidence to which the model is exposed during…

Computation and Language · Computer Science 2020-11-05 Tristan Thrush , Ethan Wilcox , Roger Levy
‹ Prev 1 2 3 10 Next ›