English
Related papers

Related papers: Analyzing Encoded Concepts in Transformer Language…

200 papers

We study the problem of multilingual masked language modeling, i.e. the training of a single model on concatenated text from multiple languages, and present a detailed study of several factors that influence why these models are so…

Computation and Language · Computer Science 2020-05-11 Shijie Wu , Alexis Conneau , Haoran Li , Luke Zettlemoyer , Veselin Stoyanov

Autoencoders exhibit impressive abilities to embed the data manifold into a low-dimensional latent space, making them a staple of representation learning methods. However, without explicit supervision, which is often unavailable, the…

Machine Learning · Computer Science 2023-01-12 Felix Leeb , Stefan Bauer , Michel Besserve , Bernhard Schölkopf

Multilingual language models (MLLMs) have demonstrated remarkable abilities to transfer knowledge across languages, despite being trained without explicit cross-lingual supervision. We analyze the parameter spaces of three MLLMs to study…

Computation and Language · Computer Science 2025-06-03 Frederick Riemenschneider , Anette Frank

This paper proposes a novel deep subspace clustering approach which uses convolutional autoencoders to transform input images into new representations lying on a union of linear subspaces. The first contribution of our work is to insert…

Computer Vision and Pattern Recognition · Computer Science 2020-01-24 Mohsen Kheirandishfard , Fariba Zohrizadeh , Farhad Kamangar

Cross-lingual transfer learning is an important property of multilingual large language models (LLMs). But how do LLMs represent relationships between languages? Every language model has an input layer that maps tokens to vectors. This…

Computation and Language · Computer Science 2023-12-19 Andrea W Wen-Yi , David Mimno

We propose a Deep Texture Encoding Network (Deep-TEN) with a novel Encoding Layer integrated on top of convolutional layers, which ports the entire dictionary learning and encoding pipeline into a single model. Current methods build from…

Computer Vision and Pattern Recognition · Computer Science 2016-12-12 Hang Zhang , Jia Xue , Kristin Dana

We investigate what kind of structural knowledge learned in neural network encoders is transferable to processing natural language. We design artificial languages with structural properties that mimic natural language, pretrain encoders on…

Computation and Language · Computer Science 2022-03-23 Ryokan Ri , Yoshimasa Tsuruoka

Deep transformer models have pushed performance on NLP tasks to new limits, suggesting sophisticated treatment of complex linguistic inputs, such as phrases. However, we have limited understanding of how these models handle representation…

Computation and Language · Computer Science 2020-10-15 Lang Yu , Allyson Ettinger

Concept-based models aim to explain model decisions with human-understandable concepts. However, most existing approaches treat concepts as numerical attributes, without providing complementary visual explanations that could localize the…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Cristiano Patrício , Luís F. Teixeira , João C. Neves

The proliferation of deep neural networks in various domains has seen an increased need for the interpretability of these models, especially in scenarios where fairness and trust are as important as model performance. A lot of independent…

Computation and Language · Computer Science 2023-03-07 Fahim Dalvi , Nadir Durrani , Hassan Sajjad , Tamim Jaban , Musab Husaini , Ummar Abbas

Large Transformer-based language models can aid human authors by suggesting plausible continuations of text written so far. However, current interactive writing assistants do not allow authors to guide text generation in desired topical…

Computation and Language · Computer Science 2021-03-30 Haw-Shiuan Chang , Jiaming Yuan , Mohit Iyyer , Andrew McCallum

We introduce a dataset of concept learning tasks that helps uncover implicit biases in large language models. Using in-context concept learning experiments, we found that language models may have a bias toward upward monotonicity in…

Computation and Language · Computer Science 2025-11-27 Leroy Z. Wang

While there is much recent interest in studying why Transformer-based large language models make predictions the way they do, the complex computations performed within each layer have made their behavior somewhat opaque. To mitigate this…

Computation and Language · Computer Science 2023-06-06 Byung-Doh Oh , William Schuler

Human speakers can generate descriptions of perceptual concepts, abstracted from the instance-level. Moreover, such descriptions can be used by other speakers to learn provisional representations of those concepts. Learning and using…

Computation and Language · Computer Science 2023-10-27 Bill Noble , Nikolai Ilinykh

Advancements in audio neural networks have established state-of-the-art results on downstream audio tasks. However, the black-box structure of these models makes it difficult to interpret the information encoded in their internal audio…

Sound · Computer Science 2025-04-22 Alice Zhang , Edison Thomaz , Lie Lu

Recent advancements in unsupervised feature learning have developed powerful latent representations of words. However, it is still not clear what makes one representation better than another and how we can learn the ideal representation.…

Machine Learning · Computer Science 2014-06-30 Bryan Perozzi , Rami Al-Rfou , Vivek Kulkarni , Steven Skiena

Fine-tuned transformer models have shown superior performances in many natural language tasks. However, the large model size prohibits deploying high-performance transformer models on resource-constrained devices. This paper proposes a…

Computation and Language · Computer Science 2024-10-01 Zi Yang , Samridhi Choudhary , Siegfried Kunzmann , Zheng Zhang

Recent works show that discourse analysis benefits from modeling intra- and inter-sentential levels separately, where proper representations for text units of different granularities are desired to capture both the meaning of text units and…

Computation and Language · Computer Science 2022-05-05 Yifei Zhou , Yansong Feng

Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…

Machine Learning · Statistics 2026-03-18 Nuri Mert Vural , Alberto Bietti , Mahdi Soltanolkotabi , Denny Wu

Transforming a large language model (LLM) into a Vision-Language Model (VLM) can be achieved by mapping the visual tokens from a vision encoder into the embedding space of an LLM. Intriguingly, this mapping can be as simple as a shallow MLP…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Benno Krojer , Shravan Nayak , Oscar Mañas , Vaibhav Adlakha , Desmond Elliott , Siva Reddy , Marius Mosbach