English
Related papers

Related papers: Tracing and Manipulating Intermediate Values in Ne…

200 papers

Linguistic representation learning in deep neural language models (LMs) has been studied for decades, for both practical and theoretical reasons. However, finding representations in LMs remains an unsolved problem, in part due to a dilemma…

Computation and Language · Computer Science 2026-03-26 Joshua Rozner , Cory Shain

We investigate the mechanisms that arise when transformers are trained to solve arithmetic on sequences where tokens are variables whose meaning is determined only through their interactions in-context. While prior work has studied…

Computation and Language · Computer Science 2026-02-26 Eric Todd , Jannik Brinkmann , Rohit Gandikota , David Bau

Accent variability remains a major errors in automatic speech recognition, yet most adaptation methods rely on parameter fine-tuning without understanding where accent information is encoded. We treat accent variation as an interpretable…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-09 Jinuo Sun , Yang Xiao , Sung Kyun Chung , Qiuchi Hu , Gongping Huang , Eun-Jung Holden , Ting Dang

In the task of machine translation, context information is one of the important factor. But considering the context information model dose not proposed. The paper propose a new model which can integrate context information and make…

Computation and Language · Computer Science 2019-04-02 Tetsuto Takano , Satoshi Yamane

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

Multi-layer models with multiple attention heads per layer provide superior translation quality compared to simpler and shallower models, but determining what source context is most relevant to each target word is more challenging as a…

Computation and Language · Computer Science 2019-02-01 Thomas Zenkel , Joern Wuebker , John DeNero

Neural sequence models, especially transformers, exhibit a remarkable capacity for in-context learning. They can construct new predictors from sequences of labeled examples $(x, f(x))$ presented in the input without further parameter…

Machine Learning · Computer Science 2023-05-19 Ekin Akyürek , Dale Schuurmans , Jacob Andreas , Tengyu Ma , Denny Zhou

Transformer-based language models have achieved significant success; however, their internal mechanisms remain largely opaque due to the complexity of non-linear interactions and high-dimensional operations. While previous studies have…

Artificial Intelligence · Computer Science 2025-02-17 Lin Zhang , Lijie Hu , Di Wang

Transformers have shown impressive capabilities across various tasks, but their performance on compositional problems remains a topic of debate. In this work, we investigate the mechanisms of how transformers behave on unseen compositional…

Machine Learning · Computer Science 2025-01-14 Zhongwang Zhang , Pengxiao Lin , Zhiwei Wang , Yaoyu Zhang , Zhi-Qin John Xu

With the ever-increasing complexity of neural language models, practitioners have turned to methods for understanding the predictions of these models. One of the most well-adopted approaches for model interpretability is feature-based…

Computation and Language · Computer Science 2021-06-10 Muhammad Bilal Zafar , Michele Donini , Dylan Slack , Cédric Archambeau , Sanjiv Das , Krishnaram Kenthapadi

Many visual scenes contain text that carries crucial information, and it is thus essential to understand text in images for downstream reasoning tasks. For example, a deep water label on a warning sign warns people about the danger in the…

Computer Vision and Pattern Recognition · Computer Science 2020-03-26 Ronghang Hu , Amanpreet Singh , Trevor Darrell , Marcus Rohrbach

Inference models are a key component in scaling variational inference to deep latent variable models, most notably as encoder networks in variational auto-encoders (VAEs). By replacing conventional optimization-based inference with a…

Machine Learning · Computer Science 2018-07-26 Joseph Marino , Yisong Yue , Stephan Mandt

Rapid integration of large language models (LLMs) into societal applications has intensified concerns about their alignment with universal ethical principles, as their internal value representations remain opaque despite behavioral…

Computation and Language · Computer Science 2025-05-26 Yi Su , Jiayi Zhang , Shu Yang , Xinhai Wang , Lijie Hu , Di Wang

Understanding the internal representations of large language models (LLMs) is a central challenge in interpretability research. Existing feature interpretability methods often rely on strong assumptions about the structure of…

Machine Learning · Computer Science 2025-09-30 Yifan Luo , Zhennan Zhou , Bin Dong

The key to success in machine learning (ML) is the use of effective data representations. Traditionally, data representations were hand-crafted. Recently it has been demonstrated that, given sufficient data, deep neural networks can learn…

Machine Learning · Computer Science 2018-11-09 Ivan Olier , Oghenejokpeme I. Orhobor , Joaquin Vanschoren , Ross D. King

We present time vectors, a simple tool to customize language models to new time periods. Time vectors are created by finetuning a language model on data from a single time (e.g., a year or month), and then subtracting the weights of the…

Computation and Language · Computer Science 2024-01-02 Kai Nylund , Suchin Gururangan , Noah A. Smith

Induction head mechanism is a part of the computational circuits for in-context learning (ICL) that enable large language models (LLMs) to adapt to new tasks without fine-tuning. Most existing work explains the training dynamics behind…

Computation and Language · Computer Science 2025-07-09 Shuo Wang , Issei Sato

Although neural models have achieved impressive results on several NLP benchmarks, little is understood about the mechanisms they use to perform language tasks. Thus, much recent attention has been devoted to analyzing the sentence…

Computation and Language · Computer Science 2021-03-09 Abhilasha Ravichander , Yonatan Belinkov , Eduard Hovy

Progress in pre-trained language models has led to a surge of impressive results on downstream tasks for natural language understanding. Recent work on probing pre-trained language models uncovered a wide range of linguistic properties…

Computation and Language · Computer Science 2022-03-22 Zeming Chen , Qiyue Gao

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