Related papers: The Instruction Hierarchy: Training LLMs to Priori…
When LLMs are deployed in sensitive, human-facing settings, it is crucial that they do not output unsafe, biased, or privacy-violating outputs. For this reason, models are both trained and instructed to refuse to answer unsafe prompts such…
Inspired by the exceptional general intelligence of Large Language Models (LLMs), researchers have begun to explore their application in pioneering the next generation of recommender systems - systems that are conversational, explainable,…
As large language models (LLMs) are increasingly deployed in enterprise settings, controlling model behavior based on user roles becomes an essential requirement. Existing safety methods typically assume uniform access and focus on…
Instruction-tuning enhances the ability of large language models (LLMs) to follow user instructions more accurately, improving usability while reducing harmful outputs. However, this process may increase the model's dependence on user…
Instruction-tuning plays a vital role in enhancing the task-solving abilities of large language models (LLMs), improving their usability in generating helpful responses on various tasks. However, previous work has demonstrated that they are…
Instruction fine-tuning is crucial for today's large language models (LLMs) to learn to follow instructions and align with human preferences. Conventionally, supervised data, including the instruction and the correct response, is required…
Jailbreaks have been a central focus of research regarding the safety and reliability of large language models (LLMs), yet the mechanisms underlying these attacks remain poorly understood. While previous studies have predominantly relied on…
Recently, the powerful large language models (LLMs) have been instrumental in propelling the progress of recommender systems (RS). However, while these systems have flourished, their susceptibility to security threats has been largely…
Safety alignment mechanism are essential for preventing large language models (LLMs) from generating harmful information or unethical content. However, cleverly crafted prompts can bypass these safety measures without accessing the model's…
Large Language Models (LLMs) are gaining momentum in software development with prompt-driven programming enabling developers to create code from natural language (NL) instructions. However, studies have questioned their ability to produce…
Security threats like prompt injection attacks pose significant risks to applications that integrate Large Language Models (LLMs), potentially leading to unauthorized actions such as API misuse. Unlike previous approaches that aim to detect…
Prompt underspecification is a common challenge when interacting with LLMs. In this paper, we present an in-depth analysis of this problem, showing that while LLMs can often infer unspecified requirements by default (41.1%), such behavior…
Augmenting Large Language Models (LLMs) with image-understanding capabilities has resulted in a boom of high-performing Vision-Language models (VLMs). While studying the alignment of LLMs to human values has received widespread attention,…
Recently, Large language models (LLMs) with powerful general capabilities have been increasingly integrated into various Web applications, while undergoing alignment training to ensure that the generated content aligns with user intent and…
The integration of Large Language Models (LLMs) with external sources is becoming increasingly common, with Retrieval-Augmented Generation (RAG) being a prominent example. However, this integration introduces vulnerabilities of Indirect…
The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that…
Fine-tuning is a common and effective method for tailoring large language models (LLMs) to specialized tasks and applications. In this paper, we study the privacy implications of fine-tuning LLMs on user data. To this end, we consider a…
Most commonly used language models (LMs) are instruction-tuned and aligned using a combination of fine-tuning and reinforcement learning, causing them to refuse users requests deemed harmful by the model. However, jailbreak prompts can…
For well over a quarter century, detection systems have been driven by models learned from input features collected from real or simulated environments. An artifact (e.g., network event, potential malware sample, suspicious email) is deemed…
Instruction-following is a fundamental ability of Large Language Models (LLMs), requiring their generated outputs to follow multiple constraints imposed in input instructions. Numerous studies have attempted to enhance this ability through…