English
Related papers

Related papers: Toward a Theory of Causation for Interpreting Neur…

200 papers

Neural Linear Models (NLM) are deep Bayesian models that produce predictive uncertainty by learning features from the data and then performing Bayesian linear regression over these features. Despite their popularity, few works have focused…

Machine Learning · Statistics 2021-06-25 Cooper Lorsung

Deep neural networks have achieved impressive supervised classification performance in many tasks including image recognition, speech recognition, and sequence to sequence learning. However, this success has not been translated to…

Machine Learning · Computer Science 2016-08-05 Arvind Neelakantan , Quoc V. Le , Ilya Sutskever

As Large Language Models (LLMs) become increasingly integrated into our daily lives, the potential harms from deceptive behavior underlie the need for faithfully interpreting their decision-making. While traditional probing methods have…

Machine Learning · Computer Science 2024-11-08 Anthony Costarelli , Mat Allen , Severin Field

Neural networks are among the most accurate supervised learning methods in use today, but their opacity makes them difficult to trust in critical applications, especially when conditions in training differ from those in test. Recent work on…

Machine Learning · Computer Science 2017-11-15 Andrew Slavin Ross , Michael C. Hughes , Finale Doshi-Velez

Large Language Models (LLMs) have achieved remarkable success in tasks requiring complex reasoning, such as code generation, mathematical problem solving, and algorithmic synthesis -- especially when aided by reasoning tokens and…

Computation and Language · Computer Science 2025-06-13 Jaechul Roh , Varun Gandhi , Shivani Anilkumar , Arin Garg

Neural generative models can be used to learn complex probability distributions from data, to sample from them, and to produce probability density estimates. We propose a computational framework for developing neural generative models…

Machine Learning · Computer Science 2022-01-06 Alexander Ororbia , Daniel Kifer

Can language models (LMs) learn to faithfully describe their internal computations? Are they better able to describe themselves than other models? We study the extent to which LMs' privileged access to their own internals can be leveraged…

Computation and Language · Computer Science 2026-02-10 Belinda Z. Li , Zifan Carl Guo , Vincent Huang , Jacob Steinhardt , Jacob Andreas

Predictive coding (PC) is an influential theory in computational neuroscience, which argues that the cortex forms unsupervised world models by implementing a hierarchical process of prediction error minimization. PC networks (PCNs) are…

Neural and Evolutionary Computing · Computer Science 2022-08-05 Beren Millidge , Yuhang Song , Tommaso Salvatori , Thomas Lukasiewicz , Rafal Bogacz

Although deep learning models have been successfully applied to a variety of tasks, due to the millions of parameters, they are becoming increasingly opaque and complex. In order to establish trust for their widespread commercial use, it is…

Machine Learning · Computer Science 2018-11-13 Tanmayee Narendra , Anush Sankaran , Deepak Vijaykeerthy , Senthil Mani

Deep neural networks have significantly improved the performance of low-level vision tasks but also increased the difficulty of interpretability. A deep understanding of deep models is beneficial for both network design and practical…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Jinfan Hu , Jinjin Gu , Shiyao Yu , Fanghua Yu , Zheyuan Li , Zhiyuan You , Chaochao Lu , Chao Dong

Several recent studies have shown that strong natural language understanding (NLU) models are prone to relying on unwanted dataset biases without learning the underlying task, resulting in models that fail to generalize to out-of-domain…

Computation and Language · Computer Science 2020-04-27 Rabeeh Karimi Mahabadi , Yonatan Belinkov , James Henderson

Reasoning models (RMs), language models (LMs) trained with reinforcement learning to produce long-form natural language reasoning, have been remarkably successful, but they still require large amounts of computation and data to train, and…

Computation and Language · Computer Science 2025-10-27 Cedegao E. Zhang , Cédric Colas , Gabriel Poesia , Joshua B. Tenenbaum , Jacob Andreas

Leveraging recent advancements in large language models, modern neural code completion models have demonstrated the capability to generate highly accurate code suggestions. However, their massive size poses challenges in terms of…

Software Engineering · Computer Science 2024-01-19 Zhensu Sun , Xiaoning Du , Fu Song , Shangwen Wang , Li Li

Pre-trained language models have demonstrated powerful capabilities in the field of natural language processing (NLP). Recently, code pre-trained model (PTM), which draw from the experiences of the NLP field, have also achieved…

Software Engineering · Computer Science 2023-11-15 Yu Zhao , Lina Gong , Haoxiang Zhang , Yaoshen Yu , Zhiqiu Huang

We present DoWhy-GCM, an extension of the DoWhy Python library, which leverages graphical causal models. Unlike existing causality libraries, which mainly focus on effect estimation, DoWhy-GCM addresses diverse causal queries, such as…

Research at the intersection of machine learning, programming languages, and software engineering has recently taken important steps in proposing learnable probabilistic models of source code that exploit code's abundance of patterns. In…

Software Engineering · Computer Science 2018-05-08 Miltiadis Allamanis , Earl T. Barr , Premkumar Devanbu , Charles Sutton

Neurally-parameterized Structural Causal Models in the Pearlian notion to causality, referred to as NCM, were recently introduced as a step towards next-generation learning systems. However, said NCM are only concerned with the learning…

Machine Learning · Computer Science 2022-12-27 Matej Zečević , Devendra Singh Dhami , Kristian Kersting

With the great success of pre-trained models, the pretrain-then-finetune paradigm has been widely adopted on downstream tasks for source code understanding. However, compared to costly training a large-scale model from scratch, how to…

Software Engineering · Computer Science 2022-03-16 Deze Wang , Zhouyang Jia , Shanshan Li , Yue Yu , Yun Xiong , Wei Dong , Xiangke Liao

Causal reasoning is viewed as crucial for achieving human-level machine intelligence. Recent advances in language models have expanded the horizons of artificial intelligence across various domains, sparking inquiries into their potential…

Computation and Language · Computer Science 2024-05-02 Sirui Chen , Bo Peng , Meiqi Chen , Ruiqi Wang , Mengying Xu , Xingyu Zeng , Rui Zhao , Shengjie Zhao , Yu Qiao , Chaochao Lu

Finding important features that contribute to the prediction of neural models is an active area of research in explainable AI. Neural models are opaque and finding such features sheds light on a better understanding of their predictions. In…

Machine Learning · Computer Science 2023-08-15 Md Rafiqul Islam Rabin , Aftab Hussain , Sahil Suneja , Mohammad Amin Alipour