相关论文: Adversarial Alignment: Ensuring Value Consistency …

Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can…

Aligning large language models (LLMs) to value systems has emerged as a significant area of research within the fields of AI and NLP. Currently, this alignment process relies on the availability of high-quality supervised and preference…

Large Language Models (LLMs) are becoming vital tools that help us solve and understand complex problems by acting as digital assistants. LLMs can generate convincing explanations, even when only given the inputs and outputs of these…

Large language models (LLMs) with explicit reasoning capabilities excel at mathematical reasoning yet still commit process errors, such as incorrect calculations, brittle logic, and superficially plausible but invalid steps. In this paper,…

Achieving adversarial robustness in Vision-Language Models (VLMs) inevitably compromises accuracy on clean data, presenting a long-standing and challenging trade-off. In this work, we revisit this trade-off by investigating a fundamental…

The proliferation of Large Language Models (LLMs), such as ChatGPT, has raised concerns about their potential impact on academic integrity, prompting the need for LLM-resistant exam designs. This article investigates the performance of LLMs…

Alignment has become a critical step for instruction-tuned Large Language Models (LLMs) to become helpful assistants. However, the effective evaluation of alignment for emerging Chinese LLMs is still largely unexplored. To fill in this gap,…

Large Language Models (LLMs) are powerful zero-shot assessors used in real-world situations such as assessing written exams and benchmarking systems. Despite these critical applications, no existing work has analyzed the vulnerability of…

Adversarial training, which minimizes the maximal risk for label-preserving input perturbations, has proved to be effective for improving the generalization of language models. In this work, we propose a novel adversarial training…

With the rapid development of large language models (LLMs), they are not only used as general-purpose AI assistants but are also customized through further fine-tuning to meet the requirements of different applications. A pivotal factor in…

Large vision-language models (VLMs) such as GPT-4 have achieved unprecedented performance in response generation, especially with visual inputs, enabling more creative and adaptable interaction than large language models such as ChatGPT.…

Suicidal risk detection in adolescents is a critical challenge, yet existing methods rely on language-specific models, limiting scalability and generalization. This study introduces a novel language-agnostic framework for suicidal risk…

This research investigates the effectiveness of established vulnerability metrics, such as the Common Vulnerability Scoring System (CVSS), in evaluating attacks against Large Language Models (LLMs), with a focus on Adversarial Attacks…

Prior research has revealed that certain abstract concepts are linearly represented as directions in the representation space of LLMs, predominantly centered around English. In this paper, we extend this investigation to a multilingual…

Fine-tuning large language models (LLMs) for alignment typically relies on supervised fine-tuning or reinforcement learning from human feedback, both limited by the cost and scarcity of high-quality annotations. Recent self-play and…

Large Language Models (LLMs) can elicit unintended and even harmful content when misaligned with human values, posing severe risks to users and society. To mitigate these risks, current evaluation benchmarks predominantly employ…

Model quantization is critical for deploying large language models (LLMs) on resource-constrained hardware, yet recent work has revealed severe security risks that benign LLMs in full precision may exhibit malicious behaviors after…

In-context learning enables large language models (LLMs) to perform a variety of tasks, including learning to make reward-maximizing choices in simple bandit tasks. Given their potential use as (autonomous) decision-making agents, it is…

Vision-language models (VLMs) have significantly advanced autonomous driving (AD) by enhancing reasoning capabilities. However, these models remain highly vulnerable to adversarial attacks. While existing research has primarily focused on…

Large Language Models (LLMs) are increasingly deployed in socially complex, interaction-driven tasks, yet their ability to mirror human behavior in emotionally and strategically complex contexts remains underexplored. This study assesses…