English
Related papers

Related papers: Interpreting and Controlling Model Behavior via Co…

200 papers

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

Recently, interpretable machine learning has re-explored concept bottleneck models (CBM). An advantage of this model class is the user's ability to intervene on predicted concept values, affecting the downstream output. In this work, we…

Machine Learning · Computer Science 2024-10-29 Sonia Laguna , Ričards Marcinkevičs , Moritz Vandenhirtz , Julia E. Vogt

Interpretability analysis methods for artificial intelligence models, such as LIME and SHAP, are widely used, though they primarily serve as post-model for analyzing model outputs. While it is commonly believed that the transparency and…

General Finance · Quantitative Finance 2025-02-28 Yan Zhang , Lin Chen , Yixiang Tian

Using attention weights to identify information that is important for models' decision-making is a popular approach to interpret attention-based neural networks. This is commonly realized in practice through the generation of a heat-map for…

Information Retrieval · Computer Science 2021-06-01 Tian Shi , Xuchao Zhang , Ping Wang , Chandan K. Reddy

Vision systems to see and reason about the compositional nature of visual scenes are fundamental to understanding our world. The complex relations between objects and their locations, ambiguities, and variations in the real-world…

Computer Vision and Pattern Recognition · Computer Science 2023-07-27 Muhammad Awais , Muzammal Naseer , Salman Khan , Rao Muhammad Anwer , Hisham Cholakkal , Mubarak Shah , Ming-Hsuan Yang , Fahad Shahbaz Khan

Formal/symbolic semantics can provide canonical, rigid controllability and interpretability to sentence representations due to their \textit{localisation} or \textit{composition} property. How can we deliver such property to the current…

Computation and Language · Computer Science 2025-07-02 Yingji Zhang , Danilo S. Carvalho , André Freitas

We present a machine-checked formalization of structurally governed AI workflow architectures and prove that effect-level governance can be imposed without reducing internal computational expressivity. Using Interaction Trees in Rocq 8.19,…

Artificial Intelligence · Computer Science 2026-05-27 Alan L. McCann

As Large Language Models are deployed within Artificial Intelligence systems, that are increasingly integrated with human society, it becomes more important than ever to study their internal structures. Higher level abilities of LLMs such…

Computation and Language · Computer Science 2023-09-19 Stephen Fitz

Concept Bottleneck Models (CBMs) have garnered much attention for their ability to elucidate the prediction process through a human-understandable concept layer. However, most previous studies focused on static scenarios where the data and…

Machine Learning · Computer Science 2026-01-05 Hongbin Lin , Chenyang Ren , Juangui Xu , Zhengyu Hu , Cheng-Long Wang , Yao Shu , Hui Xiong , Jingfeng Zhang , Di Wang , Lijie Hu

A robot's ability to understand or ground natural language instructions is fundamentally tied to its knowledge about the surrounding world. We present an approach to grounding natural language utterances in the context of factual…

Robotics · Computer Science 2018-11-19 Rohan Paul , Andrei Barbu , Sue Felshin , Boris Katz , Nicholas Roy

Chain-of-thought (CoT) prompting is widely used as a reasoning aid and is often treated as a transparency mechanism. Yet behavioral gains under CoT do not imply that the model's internal computation causally depends on the emitted reasoning…

Machine Learning · Computer Science 2026-02-10 Anish Sathyanarayanan , Aditya Nagarsekar , Aarush Rathore

Language model (LM) assistants are increasingly used in applications such as brainstorming and research. Improvements in memory and context size have allowed these models to become more autonomous, which has also resulted in more text…

Computation and Language · Computer Science 2025-11-05 Jiayi Geng , Howard Chen , Ryan Liu , Manoel Horta Ribeiro , Robb Willer , Graham Neubig , Thomas L. Griffiths

The field of text-to-image (T2I) generation has garnered significant attention both within the research community and among everyday users. Despite the advancements of T2I models, a common issue encountered by users is the need for…

Computation and Language · Computer Science 2023-10-31 Wanrong Zhu , Xinyi Wang , Yujie Lu , Tsu-Jui Fu , Xin Eric Wang , Miguel Eckstein , William Yang Wang

Pre-trained language models (PLMs) like BERT are being used for almost all language-related tasks, but interpreting their behavior still remains a significant challenge and many important questions remain largely unanswered. In this work,…

Computation and Language · Computer Science 2021-09-28 Samuel Stevens , Yu Su

Despite the remarkable generation capabilities of diffusion models, recent studies have shown that they can memorize and create harmful content when given specific text prompts. Although fine-tuning approaches have been developed to…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Siyi Chen , Yimeng Zhang , Sijia Liu , Qing Qu

How interpretable are the features of leading vision models? The question is increasingly pressing as these models move from research benchmarks into high-stakes deployments, yet existing methods cannot answer it reliably. We close this gap…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Julien Colin , Lore Goetschalckx , Nuria Oliver , Thomas Serre

Advancements in foundation models (FMs) have led to a paradigm shift in machine learning. The rich, expressive feature representations from these pre-trained, large-scale FMs are leveraged for multiple downstream tasks, usually via…

Machine Learning · Computer Science 2024-12-19 Jihye Choi , Jayaram Raghuram , Yixuan Li , Somesh Jha

Critical points separate distinct dynamical regimes of complex systems, often delimiting functional or macroscopic phases in which the system operates. However, the long-term prediction of critical regimes and behaviors is challenging given…

Physics and Society · Physics 2025-04-15 Xiangrong Wang , Dan Lu , Zongze Wu , Weina Xu , Hongru Hou , Yanqing Hu , Yamir Moreno

An LLM's factuality and refusal training can be compromised by simple changes to a prompt. Models often adopt user beliefs (sycophancy) or satisfy inappropriate requests which are wrapped within special text (jailbreaking). We explore…

Machine Learning · Computer Science 2025-11-03 Alex Irpan , Alexander Matt Turner , Mark Kurzeja , David K. Elson , Rohin Shah

To go from (passive) process monitoring to active process control, an effective AI system must learn about the behavior of the complex system from very limited training data, forming an ad-hoc digital twin with respect to process inputs and…

‹ Prev 1 8 9 10 Next ›