English
Related papers

Related papers: Interpreto: An Explainability Library for Transfor…

200 papers

While recent advancements in Neural Ranking Models have resulted in significant improvements over traditional statistical retrieval models, it is generally acknowledged that the use of large neural architectures and the application of…

Information Retrieval · Computer Science 2025-05-13 Sourav Saha , Harsh Agarwal , V Venktesh , Avishek Anand , Swastik Mohanty , Debapriyo Majumdar , Mandar Mitra

The scale, variety, and quantity of publicly-available NLP datasets has grown rapidly as researchers propose new tasks, larger models, and novel benchmarks. Datasets is a community library for contemporary NLP designed to support this…

We provide a novel notion of what it means to be interpretable, looking past the usual association with human understanding. Our key insight is that interpretability is not an absolute concept and so we define it relative to a target model,…

Artificial Intelligence · Computer Science 2018-10-30 Amit Dhurandhar , Vijay Iyengar , Ronny Luss , Karthikeyan Shanmugam

We present minicons, an open source library that provides a standard API for researchers interested in conducting behavioral and representational analyses of transformer-based language models (LMs). Specifically, minicons enables…

Computation and Language · Computer Science 2022-03-25 Kanishka Misra

Interpretability is essential for deploying object detection systems in critical applications, especially under low-quality imaging conditions that degrade visual information and increase prediction uncertainty. Existing methods either…

Computer Vision and Pattern Recognition · Computer Science 2026-04-16 Jianlin Xiang , Linhui Dai , Xue Yang , Chaolei Yang , Yanshan Li

The current modus operandi in NLP involves downloading and fine-tuning pre-trained models consisting of millions or billions of parameters. Storing and sharing such large trained models is expensive, slow, and time-consuming, which impedes…

Computation and Language · Computer Science 2020-10-07 Jonas Pfeiffer , Andreas Rücklé , Clifton Poth , Aishwarya Kamath , Ivan Vulić , Sebastian Ruder , Kyunghyun Cho , Iryna Gurevych

Prototypical methods have recently gained a lot of attention due to their intrinsic interpretable nature, which is obtained through the prototypes. With growing use cases of model reuse and distillation, there is a need to also study…

Computer Vision and Pattern Recognition · Computer Science 2022-05-04 Monish Keswani , Sriranjani Ramakrishnan , Nishant Reddy , Vineeth N Balasubramanian

Large Language Models (LLMs) recently demonstrated capabilities for generating source code in common programming languages. Additionally, commercial products such as ChatGPT 4 started to provide code interpreters, allowing for the automatic…

Software Engineering · Computer Science 2023-11-15 Felix Härer

Many NLP applications require models to be interpretable. However, many successful neural architectures, including transformers, still lack effective interpretation methods. A possible solution could rely on building explanations from…

Computation and Language · Computer Science 2024-04-04 Federico Ruggeri , Marco Lippi , Paolo Torroni

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

Pretrained transformer-based Language Models (LMs) are well-known for their ability to achieve significant improvement on NLP tasks, but their black-box nature, which leads to a lack of interpretability, has been a major concern. My…

Computation and Language · Computer Science 2024-12-06 Ximing Wen

We provide a novel notion of what it means to be interpretable, looking past the usual association with human understanding. Our key insight is that interpretability is not an absolute concept and so we define it relative to a target model,…

Artificial Intelligence · Computer Science 2017-07-14 Amit Dhurandhar , Vijay Iyengar , Ronny Luss , Karthikeyan Shanmugam

Locating and editing knowledge in large language models (LLMs) is crucial for enhancing their accuracy, safety, and inference rationale. We introduce ``concept editing'', an innovative variation of knowledge editing that uncovers…

Computation and Language · Computer Science 2024-08-23 Nura Aljaafari , Danilo S. Carvalho , André Freitas

The recent introduction of Transformers language representation models allowed great improvements in many natural language processing (NLP) tasks. However, if on one hand the performances achieved by this kind of architectures are…

Computation and Language · Computer Science 2023-04-03 Matteo Muffo , Enrico Bertino

Explainable AI (XAI) interfaces seek to make large language models more transparent, yet explanation alone does not produce understanding. Explaining a system's behavior is not the same as being able to engage with it, to probe and…

Human-Computer Interaction · Computer Science 2026-03-18 Gabrielle Benabdallah

Designing natural language interfaces has historically required collecting supervised data to translate user requests into carefully designed intent representations. This requires enumerating and labeling a long tail of user requests, which…

Computation and Language · Computer Science 2024-01-09 Harsh Jhamtani , Hao Fang , Patrick Xia , Eran Levy , Jacob Andreas , Ben Van Durme

With a view to provide a user-friendly interface for designing, training and developing deep learning frameworks, we have developed Expresso, a GUI tool written in Python. Expresso is built atop Caffe, the open-source, prize-winning…

Computer Vision and Pattern Recognition · Computer Science 2015-10-20 Ravi Kiran Sarvadevabhatla , R. Venkatesh Babu

Breakthroughs in transformer-based models have revolutionized not only the NLP field, but also vision and multimodal systems. However, although visualization and interpretability tools have become available for NLP models, internal…

Computer Vision and Pattern Recognition · Computer Science 2022-08-24 Estelle Aflalo , Meng Du , Shao-Yen Tseng , Yongfei Liu , Chenfei Wu , Nan Duan , Vasudev Lal

Neural networks models for NLP are typically implemented without the explicit encoding of language rules and yet they are able to break one performance record after another. This has generated a lot of research interest in interpreting the…

Computation and Language · Computer Science 2019-11-14 Mariya Toneva , Leila Wehbe

Work done to uncover the knowledge encoded within pre-trained language models rely on annotated corpora or human-in-the-loop methods. However, these approaches are limited in terms of scalability and the scope of interpretation. We propose…

Computation and Language · Computer Science 2023-10-23 Basel Mousi , Nadir Durrani , Fahim Dalvi