English
Related papers

Related papers: Beyond Accuracy: Introducing a Symbolic-Mechanisti…

200 papers

We propose an empirical measure of the approximate accuracy of feature importance estimates in deep neural networks. Our results across several large-scale image classification datasets show that many popular interpretability methods…

Machine Learning · Computer Science 2019-11-06 Sara Hooker , Dumitru Erhan , Pieter-Jan Kindermans , Been Kim

A widely held hypothesis for why generative recommendation (GR) models outperform conventional item ID-based models is that they generalize better. However, there is few systematic way to verify this hypothesis beyond a superficial…

Information Retrieval · Computer Science 2026-03-23 Yijie Ding , Zitian Guo , Jiacheng Li , Letian Peng , Shuai Shao , Wei Shao , Xiaoqiang Luo , Luke Simon , Jingbo Shang , Julian McAuley , Yupeng Hou

Symbolic regression is emerging as a promising machine learning method for learning succinct underlying interpretable mathematical expressions directly from data. Whereas it has been traditionally tackled with genetic programming, it has…

Machine Learning · Computer Science 2025-01-14 Nour Makke , Sanjay Chawla

Can Machine Learning (ML) autonomously recover interpretable mathematical structure from raw numerical data? We aim to answer this question using the classification of real-root configurations of polynomials up to degree five as a…

Numerical Analysis · Mathematics 2026-03-02 Rohan Thomas , Majid Bani-Yaghoub

Sparse Autoencoders (SAEs) are a prominent tool in mechanistic interpretability (MI) for decomposing neural network activations into interpretable features. However, the aspiration to identify a canonical set of features is challenged by…

Machine Learning · Computer Science 2025-05-27 Xiangchen Song , Aashiq Muhamed , Yujia Zheng , Lingjing Kong , Zeyu Tang , Mona T. Diab , Virginia Smith , Kun Zhang

Mechanistic interpretability (MI) aims to understand AI models by reverse-engineering the exact algorithms neural networks learn. Most works in MI so far have studied behaviors and capabilities that are trivial and token-aligned. However,…

Machine Learning · Computer Science 2024-07-15 Satvik Golechha , James Dao

Systematic Generalization refers to a learning algorithm's ability to extrapolate learned behavior to unseen situations that are distinct but semantically similar to its training data. As shown in recent work, state-of-the-art deep learning…

Artificial Intelligence · Computer Science 2020-10-06 Tong Gao , Qi Huang , Raymond J. Mooney

When machine learning supports decision-making in safety-critical systems, it is important to verify and understand the reasons why a particular output is produced. Although feature importance calculation approaches assist in…

Machine Learning · Statistics 2020-09-14 Divish Rengasamy , Benjamin Rothwell , Grazziela Figueredo

Automatic speech recognition (ASR) outcomes serve as input for downstream tasks, substantially impacting the satisfaction level of end-users. Hence, the diagnosis and enhancement of the vulnerabilities present in the ASR model bear…

Computation and Language · Computer Science 2024-01-29 Seonmin Koo , Chanjun Park , Jinsung Kim , Jaehyung Seo , Sugyeong Eo , Hyeonseok Moon , Heuiseok Lim

Large Language Models (LLMs) have shown remarkable reasoning performance but struggle with multi-step deductive reasoning involving a series of rule application steps, especially when rules are presented non-sequentially. Our preliminary…

Computation and Language · Computer Science 2024-08-27 Siyuan Wang , Zhongyu Wei , Yejin Choi , Xiang Ren

Interpretability methods aim to help users build trust in and understand the capabilities of machine learning models. However, existing approaches often rely on abstract, complex visualizations that poorly map to the task at hand or require…

Human-Computer Interaction · Computer Science 2021-07-12 Harini Suresh , Kathleen M. Lewis , John V. Guttag , Arvind Satyanarayan

Successful agent-human partnerships require that any agent generated information is understandable to the human, and that the human can easily steer the agent towards a goal. Such effective communication requires the agent to develop a…

Human-Computer Interaction · Computer Science 2025-04-24 Vikas Kushwaha , Sruti Srinivasa Ragavan , Subhajit Roy

Formal analysis to ensure adherence of software to defined architectural constraints is not yet broadly used within software development, due to the effort involved in defining formal architecture models. Within this paper, we outline…

Software Engineering · Computer Science 2025-03-21 Steffen Herbold , Christoph Knieke , Andreas Rausch , Christian Schindler

Interpretability of learning-to-rank models is a crucial yet relatively under-examined research area. Recent progress on interpretable ranking models largely focuses on generating post-hoc explanations for existing black-box ranking models,…

For optimization models to be used in practice, it is crucial that users trust the results. A key factor in this aspect is the interpretability of the solution process. A previous framework for inherently interpretable optimization models…

Optimization and Control · Mathematics 2026-02-13 Marc Goerigk , Michael Hartisch , Sebastian Merten , Kartikey Sharma

Interpretable machine learning models offer understandable reasoning behind their decision-making process, though they may not always match the performance of their black-box counterparts. This trade-off between interpretability and model…

Artificial Intelligence · Computer Science 2025-03-12 Pranjal Atrey , Michael P. Brundage , Min Wu , Sanghamitra Dutta

Many risk-sensitive applications require Machine Learning (ML) models to be interpretable. Attempts to obtain interpretable models typically rely on tuning, by trial-and-error, hyper-parameters of model complexity that are only loosely…

Machine Learning · Computer Science 2020-05-29 Marco Virgolin , Andrea De Lorenzo , Eric Medvet , Francesca Randone

Humans, animals, and modern machine learning models exhibit impressive abilities to learn complex behaviors and generalize these behaviors to unseen situations. This ability requires us to learn rules and regularities that allow for such…

Machine Learning · Computer Science 2026-05-25 Luke Cheng , Samuel Lippl

Deep sequence recognition (DSR) models receive increasing attention due to their superior application to various applications. Most DSR models use merely the target sequences as supervision without considering other related sequences,…

Computer Vision and Pattern Recognition · Computer Science 2023-06-01 Zhenghua Peng , Yu Luo , Tianshui Chen , Keke Xu , Shuangping Huang

The ability of Large Language Models (LLMs) to use external tools unlocks powerful real-world interactions, making rigorous evaluation essential. However, current benchmarks primarily report final accuracy, revealing what models can do but…

Computation and Language · Computer Science 2026-01-29 Qihao Wang , Yue Hu , Mingzhe Lu , Jiayue Wu , Yanbing Liu , Yuanmin Tang