Related papers: Putting Lipstick on Pig: Enabling Database-style W…

This paper presents a novel approach to the acquisition of language models from corpora. The framework builds on Cobweb, an early system for constructing taxonomic hierarchies of probabilistic concepts that used a tabular, attribute-value…

Deploying large language models (LLMs) is challenging because they are memory inefficient and compute-intensive for practical applications. In reaction, researchers train smaller task-specific models by either finetuning with human labels…

Handwritten archival tables contain rich historical information, yet transforming them into structured representations, such as Knowledge Graphs, requires integrating table structure recognition, handwriting recognition, and semantic…

Databases can leak confidential information when users combine query results with probabilistic data dependencies and prior knowledge. Current research offers mechanisms that either handle a limited class of dependencies or lack tractable…

Knowledge distillation transfers large teacher models to compact student models, enabling deployment on resource-limited platforms while suffering minimal performance degradation. However, this paradigm could lead to various security risks,…

Few-step diffusion or flow-based generative models typically distill a velocity-predicting teacher into a student that predicts a shortcut towards denoised data. This format mismatch has led to complex distillation procedures that often…

Starting with a collection of traces generated by process executions, process discovery is the task of constructing a simple model that describes the process, where simplicity is often measured in terms of model size. The challenge of…

A cyber-attack is a malicious attempt by experienced hackers to breach the target information system. Usually, the cyber-attacks are characterized as hybrid TTPs (Tactics, Techniques, and Procedures) and long-term adversarial behaviors,…

Python libraries often need to maintain a stable public API even as internal implementations evolve, gain new backends, or depend on heavy optional libraries. In Python, where internal objects are easy to inspect and import, users can come…

Continual learning requires models to learn continuously while preserving prior knowledge under evolving data streams. Distillation-based methods are appealing for retaining past knowledge in a shared single-model framework with low storage…

LLMs have achieved remarkable fluency and coherence in text generation, yet their widespread adoption has raised concerns about content reliability and accountability. In high-stakes domains, it is crucial to understand where and how the…

Machine learning (ML) is an increasingly important scientific tool supporting decision making and knowledge generation in numerous fields. With this, it also becomes more and more important that the results of ML experiments are…

Kernel audit logs are an invaluable source of information in the forensic investigation of a cyber-attack. However, the coarse granularity of dependency information in audit logs leads to the construction of huge attack graphs which contain…

The past few years has witnessed specialized large language model (LLM) inference systems, such as vLLM, SGLang, Mooncake, and DeepFlow, alongside rapid LLM adoption via services like ChatGPT. Driving these system design efforts is the…

Dataset distillation is an effective technique for reducing the cost and complexity of model training while maintaining performance by compressing large datasets into smaller, more efficient versions. In this paper, we present a novel…

Cyber attacks are often identified using system and network logs. There have been significant prior works that utilize provenance graphs and ML techniques to detect attacks, specifically advanced persistent threats, which are very difficult…

We propose the task of knowledge distillation detection, which aims to determine whether a student model has been distilled from a given teacher, under a practical setting where only the student's weights and the teacher's API are…

Large language models (LLMs) have become increasingly prevalent in our daily lives, leading to an expectation for LLMs to be trustworthy -- - both accurate and well-calibrated (the prediction confidence should align with its ground truth…

The carbon footprint of natural language processing research has been increasing in recent years due to its reliance on large and inefficient neural network implementations. Distillation is a network compression technique which attempts to…

Data analytics often involves hypothetical reasoning: repeatedly modifying the data and observing the induced effect on the computation result of a data-centric application. Previous work has shown that fine-grained data provenance can help…