Related papers: $\texttt{dattri}$: A Library for Efficient Data At…

The rationale behind a deep learning model's output is often difficult to understand by humans. EXplainable AI (XAI) aims at solving this by developing methods that improve interpretability and explainability of machine learning models.…

As Large Language Models (LLMs) are increasingly applied to document-based tasks - such as document summarization, question answering, and information extraction - where user requirements focus on retrieving information from provided…

We study gradient-based data attribution, aiming to identify which training examples most influence a given output. Existing methods for this task either treat network parameters uniformly or rely on implicit weighting derived from Hessian…

Training the deep neural networks that dominate NLP requires large datasets. These are often collected automatically or via crowdsourcing, and may exhibit systematic biases or annotation artifacts. By the latter we mean spurious…

Fine-tuning large pre-trained language models (LLMs) on particular datasets is a commonly employed strategy in Natural Language Processing (NLP) classification tasks. However, this approach usually results in a loss of models…

Data quality and its effective selection are fundamental to improving the performance of machine translation models, serving as cornerstones for achieving robust and reliable translation systems. This paper presents a data selection…

Modern generative search engines enhance the reliability of large language model (LLM) responses by providing cited evidence. However, evaluating the answer's attribution, i.e., whether every claim within the generated responses is fully…

The exponential growth of data storage demands has necessitated the evolution of hierarchical storage management strategies [1]. This study explores the application of streaming machine learning [3] to revolutionize data prefetching within…

Training data attribution (TDA) provides insights into which training data is responsible for a learned model behavior. Gradient-based TDA methods such as influence functions and unrolled differentiation both involve a computation that…

Effective attribution of Advanced Persistent Threats (APTs) increasingly hinges on the ability to correlate behavioral patterns and reason over complex, varied threat intelligence artifacts. We present AURA (Attribution Using…

Large Language Models (LLMs), such as GPT-4 and Llama, have demonstrated remarkable abilities in generating natural language. However, they also pose security and integrity challenges. Existing countermeasures primarily focus on…

The 3D point cloud (3DPC) has significantly evolved and benefited from the advance of deep learning (DL). However, the latter faces various issues, including the lack of data or annotated data, the existence of a significant gap between…

Modern deep learning models are notoriously opaque, which has motivated the development of methods for interpreting how deep models predict. This goal is usually approached with attribution method, which assesses the influence of features…

Attribution theory explains how individuals interpret and attribute others' behavior in a social context by employing personal (dispositional) and impersonal (situational) causality. Large Language Models (LLMs), trained on human-generated…

As an effective approach to quantify how training samples influence test sample, data attribution is crucial for understanding data and model and further enhance the transparency of machine learning models. We find that prevailing data…

The great success of Transformer-based models benefits from the powerful multi-head self-attention mechanism, which learns token dependencies and encodes contextual information from the input. Prior work strives to attribute model decisions…

Deploying models on target domain data subject to distribution shift requires adaptation. Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available…

Teaching large language models (LLMs) to generate text with citations to evidence sources can mitigate hallucinations and enhance verifiability in information-seeking systems. However, improving this capability requires high-quality…

Large language models (LLMs) are highly sensitive to even small amounts of unsafe training data, making effective detection and filtering essential for trustworthy model development. Current state-of-the-art (SOTA) detection approaches…

Feature attribution methods help make machine learning-based inference explainable by determining how much one or several features have contributed to a model's output. A particularly popular attribution method is based on the Shapley value…