English
Related papers

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

200 papers

Humans can systematically generalize to novel compositions of existing concepts. Recent studies argue that neural networks appear inherently ineffective in such cognitive capacity, leading to a pessimistic view and a lack of attention to…

Computation and Language · Computer Science 2022-10-19 Ning Shi , Boxin Wang , Wei Wang , Xiangyu Liu , Zhouhan Lin

We present an empirical analysis of the state-of-the-art systems for referring expression recognition -- the task of identifying the object in an image referred to by a natural language expression -- with the goal of gaining insight into…

Computation and Language · Computer Science 2018-05-31 Volkan Cirik , Louis-Philippe Morency , Taylor Berg-Kirkpatrick

We investigate how agents built on pretrained large language models (LLMs) can learn target classification functions from labeled examples without parameter updates. While conventional approaches like fine-tuning are often costly,…

Computation and Language · Computer Science 2026-05-06 Jackson Hassell , Dan Zhang , Hannah Kim , Tom Mitchell , Estevam Hruschka

With the growing popularity of general-purpose Large Language Models (LLMs), comes a need for more global explanations of model behaviors. Concept-based explanations arise as a promising avenue for explaining high-level patterns learned by…

Artificial Intelligence · Computer Science 2024-10-07 Meng Li , Haoran Jin , Ruixuan Huang , Zhihao Xu , Defu Lian , Zijia Lin , Di Zhang , Xiting Wang

Mechanistic interpretability aims to reverse engineer the computation performed by a neural network in terms of its internal components. Although there is a growing body of research on mechanistic interpretation of neural networks, the…

Machine Learning · Computer Science 2025-06-24 Nils Palumbo , Ravi Mangal , Zifan Wang , Saranya Vijayakumar , Corina S. Pasareanu , Somesh Jha

Neural-symbolic methods have demonstrated efficiency in enhancing the reasoning abilities of large language models (LLMs). However, existing methods mainly rely on syntactically mapping natural languages to complete formal languages like…

Computation and Language · Computer Science 2024-06-04 Yiming Wang , Zhuosheng Zhang , Pei Zhang , Baosong Yang , Rui Wang

Symbolic regression is a powerful system identification technique in industrial scenarios where no prior knowledge on model structure is available. Such scenarios often require specific model properties such as interpretability, robustness,…

Recently deep reinforcement learning has achieved tremendous success in wide ranges of applications. However, it notoriously lacks data-efficiency and interpretability. Data-efficiency is important as interacting with the environment is…

Machine Learning · Computer Science 2021-06-23 Duo Xu , Faramarz Fekri

Large Language Models (LLMs) are increasingly integrated into software engineering workflows, yet current benchmarks provide only coarse performance summaries that obscure the diverse capabilities and limitations of these models. This paper…

Software Engineering · Computer Science 2026-01-21 Felix Mächtle , Jan-Niclas Serr , Nils Loose , Thomas Eisenbarth

The trade-off between accuracy and interpretability has long been a challenge in machine learning (ML). This tension is particularly significant for emerging interpretable-by-design methods, which aim to redesign ML algorithms for…

Machine Learning · Computer Science 2025-05-28 Geyu Liang , Senne Michielssen , Salar Fattahi

Computational context understanding refers to an agent's ability to fuse disparate sources of information for decision-making and is, therefore, generally regarded as a prerequisite for sophisticated machine reasoning capabilities, such as…

Artificial Intelligence · Computer Science 2020-03-11 Alessandro Oltramari , Jonathan Francis , Cory Henson , Kaixin Ma , Ruwan Wickramarachchi

Methods for knowledge editing and unlearning in large language models seek to edit or remove undesirable knowledge or capabilities without compromising general language modeling performance. This work investigates how mechanistic…

Machine Learning · Computer Science 2024-12-06 Phillip Guo , Aaquib Syed , Abhay Sheshadri , Aidan Ewart , Gintare Karolina Dziugaite

Machine learning models that first learn a representation of a domain in terms of human-understandable concepts, then use it to make predictions, have been proposed to facilitate interpretation and interaction with models trained on…

Machine Learning · Computer Science 2020-12-08 Isaac Lage , Finale Doshi-Velez

The large size and complex decision mechanisms of state-of-the-art text classifiers make it difficult for humans to understand their predictions, leading to a potential lack of trust by the users. These issues have led to the adoption of…

The last decade has seen huge progress in the development of advanced machine learning models; however, those models are powerless unless human users can interpret them. Here we show how the mind's construction of concepts and meaning can…

Machine Learning · Statistics 2016-07-04 Nick Condry

While the need for interpretable machine learning has been established, many common approaches are slow, lack fidelity, or hard to evaluate. Amortized explanation methods reduce the cost of providing interpretations by learning a global…

Machine Learning · Statistics 2021-03-03 Neil Jethani , Mukund Sudarshan , Yindalon Aphinyanaphongs , Rajesh Ranganath

The advent of Scientific Machine Learning has heralded a transformative era in scientific discovery, driving progress across diverse domains. Central to this progress is uncovering scientific laws from experimental data through symbolic…

Methodology · Statistics 2025-09-25 Somjit Roy , Pritam Dey , Debdeep Pati , Bani K. Mallick

Large language models (LLMs) are increasingly deployed for understanding large codebases, but whether they understand operational semantics of long code context or rely on pattern matching shortcuts remains unclear. We distinguish between…

Computation and Language · Computer Science 2026-04-21 Adam Štorek , Mukur Gupta , Samira Hajizadeh , Prashast Srivastava , Suman Jana

In modern machine learning, pattern recognition replaces realtime semantic reasoning. The mapping from input to output is learned with fixed semantics by training outcomes deliberately. This is an expensive and static approach which depends…

Artificial Intelligence · Computer Science 2017-08-02 Mark Burgess

Deep learning models often suffer from a lack of interpretability due to polysemanticity, where individual neurons are activated by multiple unrelated semantics, resulting in unclear attributions of model behavior. Recent advances in…

Machine Learning · Computer Science 2024-10-30 Qi Zhang , Yifei Wang , Jingyi Cui , Xiang Pan , Qi Lei , Stefanie Jegelka , Yisen Wang