English
Related papers

Related papers: Ideal Attribution and Faithful Watermarks for Lang…

200 papers

The generative nature of Large Language Models (LLMs) is reflected in the conditional probabilities they compute to sample each response token given the previous tokens. These probabilities encode the distributional structure that the model…

Computation and Language · Computer Science 2026-05-22 Shilpika Shilpika , Carlo Graziani , Bethany Lusch , Venkatram Vishwanath , Michael E. Papka

With the rise of Machine Learning as a Service (MLaaS) platforms,safeguarding the intellectual property of deep learning models is becoming paramount. Among various protective measures, trigger set watermarking has emerged as a flexible and…

Cryptography and Security · Computer Science 2024-04-23 Hongyu Zhu , Sichu Liang , Wentao Hu , Fangqi Li , Ju Jia , Shilin Wang

With the rise of large language models (LLMs) and concerns about potential misuse, watermarks for generative LLMs have recently attracted much attention. An important aspect of such watermarks is the trade-off between their identifiability…

Cryptography and Security · Computer Science 2024-01-01 Bram Wouters

Feature attribution methods are popular in interpretable machine learning. These methods compute the attribution of each input feature to represent its importance, but there is no consensus on the definition of "attribution", leading to…

Machine Learning · Computer Science 2021-12-16 Yilun Zhou , Serena Booth , Marco Tulio Ribeiro , Julie Shah

Diffusion models have gained prominence in the image domain for their capabilities in data generation and transformation, achieving state-of-the-art performance in various tasks in both image and audio domains. In the rapidly evolving field…

Sound · Computer Science 2023-11-02 Xirong Cao , Xiang Li , Divyesh Jadav , Yanzhao Wu , Zhehui Chen , Chen Zeng , Wenqi Wei

In high-stakes domains such as healthcare and finance, effective decision-making demands not just accurate outcomes but transparent and explainable reasoning. However, current language models often lack the structured deliberation needed…

Computation and Language · Computer Science 2025-08-26 Xiusi Chen , Shanyong Wang , Cheng Qian , Hongru Wang , Peixuan Han , Heng Ji

This paper introduces a causal attribution model to enhance the interpretability of large language models (LLMs) and improve their causal reasoning abilities via precise fine-tuning. Despite LLMs' proficiency in diverse tasks, their…

Artificial Intelligence · Computer Science 2026-05-22 Hengrui Cai , Shengjie Liu , Rui Song

Recent approaches to goal recognition have leveraged planning landmarks to achieve high-accuracy with low runtime cost. These approaches, however, lack a probabilistic interpretation. Furthermore, while most probabilistic models to goal…

Artificial Intelligence · Computer Science 2021-02-24 Kin Max Gusmão , Ramon Fraga Pereira , Felipe Meneguzzi

This paper introduces a novel framework that leverages large language models (LLMs) for machine translation (MT). We start with one conjecture: an ideal translation should contain complete and accurate information for a strong enough LLM to…

Computation and Language · Computer Science 2024-11-06 Jianqiao Wangni

Property prediction accuracy has long been a key parameter of machine learning in materials informatics. Accordingly, advanced models showing state-of-the-art performance turn into highly parameterized black boxes missing interpretability.…

Materials Science · Physics 2023-08-03 Vadim Korolev , Pavel Protsenko

The explainability of machine learning algorithms is crucial, and numerous methods have emerged recently. Local, post-hoc methods assign an attribution score to each feature, indicating its importance for the prediction. However, these…

Machine Learning · Computer Science 2024-08-12 Giorgio Visani , Vincenzo Stanzione , Damien Garreau

Explaining recommendations enables users to understand whether recommended items are relevant to their needs and has been shown to increase their trust in the system. More generally, if designing explainable machine learning models is key…

Machine Learning · Computer Science 2020-08-27 Darius Afchar , Romain Hennequin

Token-level code completion is one of the most critical features in modern Integrated Development Environments (IDEs). It assists developers by suggesting relevant identifiers and APIs during coding. While completions are typically derived…

Software Engineering · Computer Science 2026-05-13 Daniele Cipollone , Egor Bogomolov , Arie van Deursen , Maliheh Izadi

Ensuring the verifiability of model answers is a fundamental challenge for retrieval-augmented generation (RAG) in the question answering (QA) domain. Recently, self-citation prompting was proposed to make large language models (LLMs)…

Computation and Language · Computer Science 2024-12-02 Jirui Qi , Gabriele Sarti , Raquel Fernández , Arianna Bisazza

Despite the widespread adoption of autoregressive language models, explainability evaluation research has predominantly focused on span infilling and masked language models. Evaluating the faithfulness of an explanation method -- how…

Computation and Language · Computer Science 2025-03-11 Sepehr Kamahi , Yadollah Yaghoobzadeh

Creating a descriptive grammar of a language is an indispensable step for language documentation and preservation. However, at the same time it is a tedious, time-consuming task. In this paper, we take steps towards automating this process…

Computation and Language · Computer Science 2020-10-07 Aditi Chaudhary , Antonios Anastasopoulos , Adithya Pratapa , David R. Mortensen , Zaid Sheikh , Yulia Tsvetkov , Graham Neubig

Feature attribution methods, which explain an individual prediction made by a model as a sum of attributions for each input feature, are an essential tool for understanding the behavior of complex deep learning models. However, ensuring…

Machine Learning · Computer Science 2020-10-28 Ethan Weinberger , Joseph Janizek , Su-In Lee

We introduce the metagame, a conceptual framework for quantifying second-order interaction effects of model explanations. For any first-order attribution $\phi(f)$ explaining a model $f$, we measure the directional influence of feature $j$…

Machine Learning · Computer Science 2026-05-08 Hubert Baniecki , Przemyslaw Biecek , Fabian Fumagalli

The advancement of Large Language Models (LLMs) has led to increasing concerns about the misuse of AI-generated text, and watermarking for LLM-generated text has emerged as a potential solution. However, it is challenging to generate…

Computation and Language · Computer Science 2024-06-11 Yepeng Liu , Yuheng Bu

This article presents a modular, component-based architecture for developing and evaluating AI agents that bridge the gap between natural language interfaces and complex enterprise data warehouses. The system directly addresses core…

Artificial Intelligence · Computer Science 2025-09-30 Nooshin Bahador