相关论文: Reasoning Robustness of LLMs to Adversarial Typogr…

Peer review is essential for maintaining academic quality, but the increasing volume of submissions places a significant burden on reviewers. Large language models (LLMs) offer potential assistance in this process, yet their susceptibility…

Large language models (LLMs) are increasingly deployed in multilingual, real-world applications with user inputs -- naturally introducing \emph{typographical errors} (typos). Yet most benchmarks assume clean input, leaving the robustness of…

Large reasoning models (LRMs) tackle complex reasoning problems by following long chain-of-thoughts (Long CoT) that incorporate reflection, backtracking, and self-validation. However, the training techniques and data requirements to elicit…

Large Language Models (LLMs) excel at various tasks, including solving math word problems (MWPs), but struggle with real-world problems containing irrelevant information. To address this, we propose a prompting framework that generates…

Robust verbal confidence generated by large language models (LLMs) is crucial for the deployment of LLMs to help ensure transparency, trust, and safety in many applications, including those involving human-AI interactions. In this paper, we…

Reasoning LLMs (RLLMs) generate step-by-step chains of thought (CoTs) before giving an answer, which improves performance on complex tasks and makes reasoning more transparent. But how robust are these reasoning traces to disruptions that…

The increasing deployment of large language models (LLMs) in safety-critical applications raises fundamental challenges in systematically evaluating robustness against adversarial behaviors. Existing red-teaming practices are largely manual…

Despite recent efforts in Large Language Model (LLM) safety and alignment, current adversarial attacks on frontier LLMs can still consistently force harmful generations. Although adversarial training has been widely studied and shown to…

Recent studies demonstrated that large language models (LLMs) can excel in many tasks via in-context learning (ICL). However, recent works show that ICL-prompted models tend to produce inaccurate results when presented with adversarial…

As powerful Large Language Models (LLMs) are now widely used for numerous practical applications, their safety is of critical importance. While alignment techniques have significantly improved overall safety, LLMs remain vulnerable to…

We investigate how large language models (LLMs) fail when tabular data in an otherwise canonical representation is subjected to semantic and structural distortions. Our findings reveal that LLMs lack an inherent ability to detect and…

Large Language Models (LLMs) are increasingly vulnerable to adversarial attacks that can subtly manipulate their outputs. While various defense mechanisms have been proposed, many operate as black boxes, lacking transparency in their…

The widespread use of large language models (LLMs) is increasing the demand for methods that detect machine-generated text to prevent misuse. The goal of our study is to stress test the detectors' robustness to malicious attacks under…

The integration of Artificial Intelligence (AI) within 6G networks is poised to revolutionize connectivity, reliability, and intelligent decision-making. However, the performance of AI models in these networks is crucial, as any decline can…

With the development of large language models (LLMs) like ChatGPT, both their vast applications and potential vulnerabilities have come to the forefront. While developers have integrated multiple safety mechanisms to mitigate their misuse,…

Despite advances in AI alignment, large language models (LLMs) remain vulnerable to adversarial attacks or jailbreaking, in which adversaries can modify prompts to induce unwanted behavior. While some defenses have been proposed, they have…

Large Language Models (LLMs) have recently demonstrated significant potential in time series forecasting, offering impressive capabilities in handling complex temporal data. However, their robustness and reliability in real-world…

Large language models (LLMs) have shown impressive capabilities, but still struggle with complex reasoning tasks requiring multiple steps. While prompt-based methods like Chain-of-Thought (CoT) can improve LLM reasoning at inference time,…

Adversarial training (AT) is an effective defense for large language models (LLMs) against jailbreak attacks, but performing AT on LLMs is costly. To improve the efficiency of AT for LLMs, recent studies propose continuous AT (CAT) that…

Recently, with the chain of thought (CoT) prompting, large language models (LLMs), e.g., GPT-3, have shown strong reasoning ability in several natural language processing tasks such as arithmetic, commonsense, and logical reasoning.…