English
Related papers

Related papers: DISCO: DISCovering Overfittings as Causal Rules fo…

200 papers

While explainability is a desirable characteristic of increasingly complex black-box models, modern explanation methods have been shown to be inconsistent and contradictory. The semantics of explanations is not always fully understood - to…

Artificial Intelligence · Computer Science 2024-08-09 Omer Reingold , Judy Hanwen Shen , Aditi Talati

Deep neural networks (DNNs) have become a crucial instrument in the software development toolkit, due to their ability to efficiently solve complex problems. Nevertheless, DNNs are highly opaque, and can behave in an unexpected manner when…

Software Engineering · Computer Science 2023-01-20 Adiel Ashrov , Guy Katz

Understanding causal relationships among features is fundamental for explaining machine learning model decisions. However, traditional causal discovery methods face challenges with categorical variables due to numerical instability in…

Artificial Intelligence · Computer Science 2026-01-30 Henry Salgado , Meagan R. Kendall , Martine Ceberio

Most of the work on interpretable machine learning has focused on designing either inherently interpretable models, which typically trade-off accuracy for interpretability, or post-hoc explanation systems, whose explanation quality can be…

Machine Learning · Computer Science 2020-11-10 Gregory Plumb , Maruan Al-Shedivat , Angel Alexander Cabrera , Adam Perer , Eric Xing , Ameet Talwalkar

Obtaining human-interpretable explanations of large, general-purpose language models is an urgent goal for AI safety. However, it is just as important that our interpretability methods are faithful to the causal dynamics underlying model…

Computation and Language · Computer Science 2024-02-08 Zhengxuan Wu , Atticus Geiger , Thomas Icard , Christopher Potts , Noah D. Goodman

Language models (LMs) have proven to be powerful tools for psycholinguistic research, but most prior work has focused on purely behavioural measures (e.g., surprisal comparisons). At the same time, research in model interpretability has…

Computation and Language · Computer Science 2024-02-21 Aryaman Arora , Dan Jurafsky , Christopher Potts

Distant supervision tackles the data bottleneck in NER by automatically generating training instances via dictionary matching. Unfortunately, the learning of DS-NER is severely dictionary-biased, which suffers from spurious correlations and…

Computation and Language · Computer Science 2021-06-18 Wenkai Zhang , Hongyu Lin , Xianpei Han , Le Sun

Conversational Search (CS) involves retrieving relevant documents from a corpus while considering the conversational context, integrating retrieval with context modeling. Recent advancements in Large Language Models (LLMs) have…

Information Retrieval · Computer Science 2025-05-19 Simon Lupart , Mohammad Aliannejadi , Evangelos Kanoulas

I argue that regularizing terms in standard regression methods not only help against overfitting finite data, but sometimes also yield better causal models in the infinite sample regime. I first consider a multi-dimensional variable…

Machine Learning · Statistics 2019-07-01 Dominik Janzing

Unlike autoregressive models, which generate tokens sequentially and benefit from reasoning-before-answering strategies such as Chain-of-Thought, Masked Diffusion Language Models (MDLMs) refine all sequence positions simultaneously, raising…

Computation and Language · Computer Science 2026-03-03 Jacob Devasier

State-of-the-art causal discovery methods usually assume that the observational data is complete. However, the missing data problem is pervasive in many practical scenarios such as clinical trials, economics, and biology. One…

Machine Learning · Computer Science 2023-01-18 Erdun Gao , Ignavier Ng , Mingming Gong , Li Shen , Wei Huang , Tongliang Liu , Kun Zhang , Howard Bondell

Large proprietary language models exhibit strong causal reasoning abilities that smaller open-source models struggle to replicate. We introduce a novel framework for distilling causal explanations that transfers causal reasoning skills from…

Computation and Language · Computer Science 2025-05-27 Aggrey Muhebwa , Khalid K. Osman

Causal discovery problems use a set of observations to deduce causality between variables in the real world, typically to answer questions about biological or physical systems. These observations are often recorded at regular time…

Signal Processing · Electrical Eng. & Systems 2026-02-24 Kurt Butler , Damian Machlanski , Panagiotis Dimitrakopoulos , Sotirios A. Tsaftaris

We introduce a causal modeling framework that captures the input-output behavior of predictive models (e.g., machine learning models). The framework enables us to identify features that directly cause the predictions, which has broad…

Machine Learning · Computer Science 2025-05-20 Yizuo Chen , Amit Bhatia

Overfitting is a phenomenon that occurs when a machine learning model is trained for too long and focused too much on the exact fitness of the training samples to the provided training labels and cannot keep track of the predictive rules…

Machine Learning · Computer Science 2025-09-22 Nuri Korhan , Samet Bayram

Identification of input data points relevant for the classifier (i.e. serve as the support vector) has recently spurred the interest of researchers for both interpretability as well as dataset debugging. This paper presents an in-depth…

Machine Learning · Computer Science 2020-09-30 Dominique Mercier , Shoaib Ahmed Siddiqui , Andreas Dengel , Sheraz Ahmed

Building a general-purpose intelligent home-assistant agent skilled in diverse tasks by human commands is a long-term blueprint of embodied AI research, which poses requirements on task planning, environment modeling, and object…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Xinyu Xu , Shengcheng Luo , Yanchao Yang , Yong-Lu Li , Cewu Lu

Discovering patterns in data that best describe the differences between classes allows to hypothesize and reason about class-specific mechanisms. In molecular biology, for example, this bears promise of advancing the understanding of…

Machine Learning · Computer Science 2023-12-08 Nils Philipp Walter , Jonas Fischer , Jilles Vreeken

Diffusion models have recently emerged as powerful tools for missing data imputation by modeling the joint distribution of observed and unobserved variables. However, existing methods, typically based on stochastic denoising diffusion…

Artificial Intelligence · Computer Science 2025-08-06 Youran Zhou , Mohamed Reda Bouadjenek , Sunil Aryal

While deep neural network models offer unmatched classification performance, they are prone to learning spurious correlations in the data. Such dependencies on confounding information can be difficult to detect using performance metrics if…

Machine Learning · Computer Science 2023-08-09 Susu Sun , Lisa M. Koch , Christian F. Baumgartner