English
Related papers

Related papers: Transformers are uninterpretable with myopic metho…

200 papers

Deep neural networks have been well-known for their superb handling of various machine learning and artificial intelligence tasks. However, due to their over-parameterized black-box nature, it is often difficult to understand the prediction…

Machine Learning · Computer Science 2022-07-18 Xuhong Li , Haoyi Xiong , Xingjian Li , Xuanyu Wu , Xiao Zhang , Ji Liu , Jiang Bian , Dejing Dou

We find limits to the Transformer architecture for language modeling and show it has a universal prediction property in an information-theoretic sense. We further analyze performance in non-asymptotic data regimes to understand the role of…

Machine Learning · Computer Science 2023-07-18 Sourya Basu , Moulik Choraria , Lav R. Varshney

Standard transformers entangle all computation in a single residual stream, obscuring which components perform which functions. We introduce the Dual-Stream Transformer, which decomposes the residual stream into two functionally distinct…

Computation and Language · Computer Science 2026-03-10 J. Clayton Kerce , Alexis Fox

We present a systematic review of 337 articles evaluating the syntactic abilities of Transformer-based language models (TLMs), reporting on over 3,000 datapoints spanning a wide range of syntactic phenomena, languages, models, and methods.…

Computation and Language · Computer Science 2026-05-28 Nora Graichen , Iria de-Dios-Flores , Gemma Boleda

People are regularly confronted with potentially deceptive statements (e.g., fake news, misleading product reviews, or lies about activities). Only few works on automated text-based deception detection have exploited the potential of deep…

Computation and Language · Computer Science 2022-10-07 Loukas Ilias , Felix Soldner , Bennett Kleinberg

Transformer architecture has become ubiquitous in the natural language processing field. To interpret the Transformer-based models, their attention patterns have been extensively analyzed. However, the Transformer architecture is not only…

Computation and Language · Computer Science 2021-09-16 Goro Kobayashi , Tatsuki Kuribayashi , Sho Yokoi , Kentaro Inui

Large Language Models (LLMs) are becoming increasingly popular in pervasive computing due to their versatility and strong performance. However, despite their ubiquitous use, the exact mechanisms underlying their outstanding performance…

Computation and Language · Computer Science 2026-02-02 Alhassan Abdelhalim , Janick Edinger , Sören Laue , Michaela Regneri

For machine learning models to be most useful in numerous sociotechnical systems, many have argued that they must be human-interpretable. However, despite increasing interest in interpretability, there remains no firm consensus on how to…

Machine Learning · Computer Science 2021-02-03 Andrew Slavin Ross , Nina Chen , Elisa Zhao Hang , Elena L. Glassman , Finale Doshi-Velez

Interpretable machine learning tackles the important problem that humans cannot understand the behaviors of complex machine learning models and how these models arrive at a particular decision. Although many approaches have been proposed, a…

Machine Learning · Computer Science 2019-05-21 Mengnan Du , Ninghao Liu , Xia Hu

Transformers have recently been shown to be capable of reliably performing logical reasoning over facts and rules expressed in natural language, but abductive reasoning - inference to the best explanation of an unexpected observation - has…

Computation and Language · Computer Science 2022-03-24 Nathan Young , Qiming Bao , Joshua Bensemann , Michael Witbrock

Despite the fact that Transformers perform well in NLP tasks, recent studies suggest that self-attention is theoretically limited in learning even some regular and context-free languages. These findings motivated us to think about their…

Computation and Language · Computer Science 2023-10-20 Shunjie Wang , Shane Steinert-Threlkeld

Finding human-understandable circuits in language models is a central goal of the field of mechanistic interpretability. We train models to have more understandable circuits by constraining most of their weights to be zeros, so that each…

Machine Learning · Computer Science 2025-11-18 Leo Gao , Achyuta Rajaram , Jacob Coxon , Soham V. Govande , Bowen Baker , Dan Mossing

Transformers have significantly advanced the field of natural language processing, but comprehending their internal mechanisms remains a challenge. In this paper, we introduce a novel geometric perspective that elucidates the inner…

Computation and Language · Computer Science 2023-09-20 Raul Molina

Transformers demonstrate impressive performance on a range of reasoning benchmarks. To evaluate the degree to which these abilities are a result of actual reasoning, existing work has focused on developing sophisticated benchmarks for…

Machine Learning · Computer Science 2024-07-02 Jannik Brinkmann , Abhay Sheshadri , Victor Levoso , Paul Swoboda , Christian Bartelt

The increasing use of complex machine learning models in education has led to concerns about their interpretability, which in turn has spurred interest in developing explainability techniques that are both faithful to the model's inner…

Machine Learning · Computer Science 2025-05-13 Juan D. Pinto , Luc Paquette

A salient approach to interpretable machine learning is to restrict modeling to simple models. In the Bayesian framework, this can be pursued by restricting the model structure and prior to favor interpretable models. Fundamentally,…

Machine Learning · Computer Science 2020-09-08 Homayun Afrabandpey , Tomi Peltola , Juho Piironen , Aki Vehtari , Samuel Kaski

The self-attention mechanism, a cornerstone of Transformer-based state-of-the-art deep learning architectures, is largely heuristic-driven and fundamentally challenging to interpret. Establishing a robust theoretical foundation to explain…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Laziz U. Abdullaev , Maksim Tkachenko , Tan M. Nguyen

Mechanistic interpretability focuses on reverse engineering the internal mechanisms learned by neural networks. We extend our focus and propose to mechanistically forward engineer using our framework based on Concept Bottleneck Models. In…

Machine Learning · Computer Science 2025-12-01 Angela van Sprang , Erman Acar , Willem Zuidema

To tackle interpretability in deep learning, we present a novel framework to jointly learn a predictive model and its associated interpretation model. The interpreter provides both local and global interpretability about the predictive…

Machine Learning · Computer Science 2022-02-24 Jayneel Parekh , Pavlo Mozharovskyi , Florence d'Alché-Buc

Transformers have dominated empirical machine learning models of natural language processing. In this paper, we introduce basic concepts of Transformers and present key techniques that form the recent advances of these models. This includes…

Computation and Language · Computer Science 2023-11-30 Tong Xiao , Jingbo Zhu