Related papers: JSON Whisperer: Efficient JSON Editing with LLMs

Differential testing can be an effective way to find bugs in software systems with multiple implementations that conform to the same specification, like compilers, network protocol parsers, or language runtimes. Specifications for such…

Although large language models (LLMs) have achieved remarkable advancements, their security remains a pressing concern. One major threat is jailbreak attacks, where adversarial prompts bypass model safeguards to generate harmful or…

Speech-driven large language models (LLMs) are increasingly accessed through speech interfaces, introducing new security risks via open acoustic channels. We present Sirens' Whisper (SWhisper), the first practical framework for covert…

Large language models (LLMs) have demonstrated impressive capabilities in code generation, where the natural language prompt plays a crucial role in conveying user intent to the model. However, prior studies have shown that LLMs are highly…

Despite efforts to align large language models (LLMs) with societal and moral values, these models remain susceptible to jailbreak attacks -- methods designed to elicit harmful responses. Jailbreaking black-box LLMs is considered…

Autoregressive Large Language Models (AR-LLMs) are widely used in software engineering (SE) but face limitations in processing code structure information and suffer from high inference latency. Diffusion LLMs (DLLMs) offer a promising…

In this paper, we make the first attempt to understand and test potential computation efficiency robustness in state-of-the-art LLMs. By analyzing the working mechanism and implementation of 20,543 public-accessible LLMs, we observe a…

The internet is saturated with low-density, high-redundancy information, such as social media comments, repetitive news, and lengthy discussions, making it difficult to extract valuable insights efficiently. Multi-layer nested JSON…

JavaScript's widespread adoption has made it an attractive target for malicious attackers who employ sophisticated obfuscation techniques to conceal harmful code. Current deobfuscation tools suffer from critical limitations that severely…

Large Language Models (LLMs) have impressive multilingual capabilities, but they suffer from unexpected code-switching, also known as language mixing, which involves switching to unexpected languages in the model response. This problem…

A crucial part of an accurate and reliable spoken language assessment system is the underlying ASR model. Recently, large-scale pre-trained ASR foundation models such as Whisper have been made available. As the output of these models is…

Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…

Prefix adders are fundamental arithmetic circuits, but their design space grows exponentially with bit-width, posing significant optimization challenges. Previous works face limitations in performance, generalization, and scalability. To…

Knowledge editing techniques, aiming to efficiently modify a minor proportion of knowledge in large language models (LLMs) without negatively impacting performance across other inputs, have garnered widespread attention. However, existing…

The application of Artificial Intelligence has become a powerful approach to detecting software vulnerabilities. However, effective vulnerability detection relies on accurately capturing the semantic structure of code and its contextual…

Large Language Models (LLMs) often retain inaccurate or outdated information from pre-training, leading to incorrect predictions or biased outputs during inference. While existing model editing methods can address this challenge, they…

Large language models (LLMs) are powerful but static; they lack mechanisms to adapt their weights in response to new tasks, knowledge, or examples. We introduce Self-Adapting LLMs (SEAL), a framework that enables LLMs to self-adapt by…

LLM agents routinely serve as first (and sometimes only) readers of academic papers, skimming for sub-claims, extracting reproducibility steps, and generalizing scope. Standard prose papers produce recurring failures in this role:…

Due to the exceptional performance of Large Language Models (LLMs) in diverse downstream tasks,there has been an exponential growth in edge-device requests to cloud-based models.However, the current authentication mechanism using static…

Large Language Models (LLMs) have recently shown strong potential in automatic program repair (APR), especially in repository-level settings where the goal is to generate patches based on natural language issue descriptions, large…