相关论文: Token-Efficient Change Detection in LLM APIs

Transformer-based models generally allocate the same amount of computation for each token in a given sequence. We develop a simple but effective "token dropping" method to accelerate the pretraining of transformer models, such as BERT,…

To drive progress in science and engineering, large language models (LLMs) must be able to process large amounts of numerical data and solve long calculations efficiently. This is currently only possible through the use of external tools or…

Recent benchmark efforts have advanced the evaluation of large language models (LLMs) in cybersecurity, including tasks such as penetration testing and vulnerability identification. However, a critical cybersecurity task, namely intrusion…

In machine learning, contamination refers to situations where testing data leak into the training set. The issue is particularly relevant for the evaluation of the performance of Large Language Models (LLMs), which are generally trained on…

Large Language Models are increasingly proposed as cognitive components for robotic systems, yet their opaque decision processes make it difficult to explain success or failure in closed-loop embodied tasks. Following an empirical AI…

In black-box large language model (LLM) services, response reliability is often only partially observable at decision time, while stronger inference pathways incur substantial computational cost, inducing a budgeted sequential decision…

This work proposes a training-free approach for the detection of LLMs-generated codes, mitigating the risks associated with their indiscriminate usage. To the best of our knowledge, our research is the first to investigate zero-shot…

Large language models (LLMs) have enabled the creation of multi-modal LLMs that exhibit strong comprehension of visual data such as images and videos. However, these models usually rely on extensive visual tokens from visual encoders,…

Instruction tuning is essential for aligning large language models (LLMs) to downstream tasks and commonly relies on large, diverse corpora. However, small, high-quality subsets, known as coresets, can deliver comparable or superior…

When a model informs decisions about people, distribution shifts can create undue disparities. However, it is hard for external entities to check for distribution shift, as the model and its training set are often proprietary. In this…

To address the growing demand for on-device LLM inference in resource-constrained environments, hybrid language models (HLM) have emerged, combining lightweight local models with powerful cloud-based LLMs. Recent studies on HLM have…

Efficient deployment of large language models (LLMs) requires extreme quantization, forcing a critical trade-off between low-bit efficiency and performance. Residual binarization enables hardware-friendly, matmul-free inference by stacking…

With new large language models (LLMs) emerging frequently, it is important to consider the potential value of model-agnostic approaches that can provide interpretability across a variety of architectures. While recent advances in LLM…

Methods for adapting language models (LMs) to new tasks and domains have traditionally assumed white-box access to the model, and work by modifying its parameters. However, this is incompatible with a recent trend in the field, where the…

Cloud applications heavily rely on APIs to communicate with each other and exchange data. To ensure the reliability of cloud applications, cloud providers widely adopt API testing techniques. Unfortunately, existing API testing approaches…

When solving optimization problems with black-box approaches, the algorithms gather valuable information about the problem instance during the optimization process. This information is used to adjust the distributions from which new…

Bringing transparency to black-box decision making systems (DMS) has been a topic of increasing research interest in recent years. Traditional active and passive approaches to make these systems transparent are often limited by scalability…

The releases of powerful open-weight large language models (LLMs) are often not accompanied by access to their full training data. Existing interpretability methods, particularly those based on activations, often require or assume…

Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. However, such access may also let malicious actors undermine model safety. To demonstrate the challenge of defending finetuning…

Using AI to create autonomous researchers has the potential to accelerate scientific discovery. A prerequisite for this vision is understanding how well an AI model can identify the underlying structure of a black-box system from its…