Related papers: CoSPED: Consistent Soft Prompt Targeted Data Extra…

Recent advancements in large language models (LLMs) integrating explicit reasoning, such as OpenAI's o3-mini, DeepSeek-R1, and QWQ-32B, enable smaller models to solve complex tasks by generating intermediate reasoning steps prior to…

Security vulnerabilities are increasingly prevalent in modern software and they are widely consequential to our society. Various approaches to defending against these vulnerabilities have been proposed, among which those leveraging deep…

Large Language Models (LLMs) have attained human-level fluency in text generation, which complicates the distinguishing between human-written and LLM-generated texts. This increases the risk of misuse and highlights the need for reliable…

Large language models (LLMs) demonstrate exceptional instruct-following ability to complete various downstream tasks. Although this impressive ability makes LLMs flexible task solvers, their performance in solving tasks also heavily relies…

With the growing adoption of Large Language Models (LLMs) in critical areas, ensuring their security against jailbreaking attacks is paramount. While traditional defenses primarily rely on refusing malicious prompts, recent logit-level…

Large language models (LLMs) can perform recommendation tasks by taking prompts written in natural language as input. Compared to traditional methods such as collaborative filtering, LLM-based recommendation offers advantages in handling…

Large Language Model (LLM) applications are vulnerable to prompt injection and context manipulation attacks that traditional security models cannot prevent. We introduce two novel primitives--authenticated prompts and authenticated…

Federated learning (FL) has enabled global model training on decentralized data in a privacy-preserving way by aggregating model updates. However, for many natural language processing (NLP) tasks that utilize pre-trained language models…

Large Language Models' safety remains a critical concern due to their vulnerability to adversarial attacks, which can prompt these systems to produce harmful responses. In the heart of these systems lies a safety classifier, a computational…

Well-designed prompts are crucial for enhancing Large language models' (LLMs) reasoning capabilities while aligning their outputs with task requirements across diverse domains. However, manually designed prompts require expertise and…

Large language model (LLM) systems increasingly power everyday AI applications such as chatbots, computer-use assistants, and autonomous robots, where performance often depends on manually well-crafted prompts. LLM-based prompt optimizers…

The surge in intelligent applications driven by large language models (LLMs) has made it increasingly difficult for bandwidth-limited cloud servers to process extensive LLM workloads in real time without compromising user data privacy. To…

Traditional benchmarks for large language models (LLMs), such as HELM and AIR-BENCH, primarily assess safety risk through breadth-oriented evaluation across diverse tasks. However, real-world deployment often exposes a different class of…

A recent trend in Natural Language Processing is the exponential growth in Language Model (LM) size, which prevents research groups without a necessary hardware infrastructure from participating in the development process. This study…

Open-source large language models (LLMs) have become increasingly popular among both the general public and industry, as they can be customized, fine-tuned, and freely used. However, some open-source LLMs require approval before usage,…

Lossless speculative decoding accelerates target large language model (LLM) inference by employing a lightweight draft model for generating tree-structured candidates, which are subsequently verified in parallel by the target LLM.…

Recently, large language models (LLMs) are capable of generating highly fluent textual content. While they offer significant convenience to humans, they also introduce various risks, like phishing and academic dishonesty. Numerous research…

Prompt tuning (PT) offers a cost-effective alternative to fine-tuning large-scale pre-trained language models (PLMs), requiring only a few parameters in soft prompt tokens added before the input text. However, existing PT approaches face…

Large Language Models (LLMs) remain vulnerable to jailbreak attacks, where adversarially crafted prompts induce policy-violating responses despite safety alignment. Existing defenses typically improve safety through external filtering,…

As large language models (LLMs) are deployed in safety-critical settings, it is essential to ensure that their responses comply with safety standards. Prior research has revealed that LLMs often fail to grasp the notion of safe behaviors,…