相关论文: Moving Faster and Reducing Risk: Using LLMs in Rel…

Large Language Models (LLMs) are typically evaluated for safety under single-shot or low-budget adversarial prompting, which underestimates real-world risk. In practice, attackers can exploit large-scale parallel sampling to repeatedly…

Structured extraction with LLMs fails in production not because models lack understanding, but because output formatting is unreliable across models and prompts. A prompt that returns clean JSON on GPT-4 may produce fenced, prose-wrapped,…

Large language models (LLMs) are increasingly deployed as economic agents in marketplaces, auctions, and bidding settings. Anticipating their behavior in any specific deployment is hard. Existing strategic-reasoning benchmarks evaluate…

Large Language Models (LLMs) with safe-alignment training are powerful instruments with robust language comprehension capabilities. These models typically undergo meticulous alignment procedures involving human feedback to ensure the…

Text generation has a fundamental limitation almost by definition: there is no taking back tokens that have been generated, even when they are clearly problematic. In the context of language model safety, when a partial unsafe generation is…

The shift from cloud-hosted Large Language Models (LLMs) to locally deployed open-source Small Language Models (SLMs) has democratized AI-assisted coding; however, it has also decentralized the environmental footprint of AI. While prompting…

Inspired by the success of deep learning (DL) in natural language processing (NLP), we applied cutting-edge DL techniques to predict flight departure demand in a strategic time horizon (4 hours or longer). This work was conducted in support…

With the increasing reliance on software and automation nowadays, tight deadlines, limited resources, and prioritization of functionality over security can lead to insecure coding practices. When not handled properly, these constraints…

An essential part of monitoring machine learning models in production is measuring input and output data drift. In this paper, we present a system for measuring distributional shifts in natural language data and highlight and investigate…

Road traffic accidents remain a major public safety and socio-economic issue in developing countries like Bangladesh. Existing accident data collection is largely manual, fragmented, and unreliable, resulting in underreporting and…

LLMs are commonly used in retrieval-augmented applications to execute user instructions based on data from external sources. For example, modern search engines use LLMs to answer queries based on relevant search results; email plugins…

Security vulnerability in third-party dependencies is a growing concern not only for developers of the affected software, but for the risks it poses to an entire software ecosystem, e.g., Heartbleed vulnerability. Recent studies show that…

Large Language Models (LLMs) are increasingly being studied for Software Vulnerability Detection (SVD) and Repair (SVR). Individual LLMs have demonstrated code understanding abilities, but they frequently struggle when identifying complex…

Large language models (LLMs) have recently achieved significant success across various application domains, garnering substantial attention from different communities. Unfortunately, even for the best LLM, many \textit{faults} still exist…

Large Language Models (LLMs) hold immense potential to generate synthetic data of high quality and utility, which has numerous applications from downstream model training to practical data utilisation. However, contemporary models, despite…

Many automated test generation techniques have been developed to aid developers with writing tests. To facilitate full automation, most existing techniques aim to either increase coverage, or generate exploratory inputs. However, existing…

In this work, we propose a novel approach, namely WeatherDG, that can generate realistic, weather-diverse, and driving-screen images based on the cooperation of two foundation models, i.e, Stable Diffusion (SD) and Large Language Model…

The fault diagnosis of rolling bearings is a critical technique to realize predictive maintenance for mechanical condition monitoring. In real industrial systems, the main challenges for the fault diagnosis of rolling bearings pertain to…

We introduce Synthetic Alignment data Generation for Safety Evaluation and Red Teaming (SAGE-RT or SAGE) a novel pipeline for generating synthetic alignment and red-teaming data. Existing methods fall short in creating nuanced and diverse…

As large language models (LLMs) continue to advance in capability and influence, ensuring their security and preventing harmful outputs has become crucial. A promising approach to address these concerns involves training models to…