相关论文: NanoFlux: Adversarial Dual-LLM Evaluation and Dist…

While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversarial attacks. However, traditional adversarial attacks are typically limited to single,…

We present that hierarchical LLM reasoning via scaling thought templates can effectively optimize the reasoning search space and outperform the mathematical reasoning capabilities of powerful LLMs like OpenAI o1-preview and DeepSeek V3. We…

The deployment of Large Language Models (LLMs) as agentic orchestrators has revolutionized task automation, but the need for privacy-preserving, cost-effective solutions demands on-device inference capabilities. However, local LLMs…

Although safely enhanced Large Language Models (LLMs) have achieved remarkable success in tackling various complex tasks in a zero-shot manner, they remain susceptible to jailbreak attacks, particularly the unknown jailbreak attack. To…

Process Reward Models (PRMs) have recently emerged as a powerful framework for supervising intermediate reasoning steps in large language models (LLMs). Previous PRMs are primarily trained on model final output responses and struggle to…

While there has been substantial research using adversarial attacks to analyze NLP models, each attack is implemented in its own code repository. It remains challenging to develop NLP attacks and utilize them to improve model performance.…

Vision-Language Models (VLMs) such as CLIP have demonstrated remarkable capabilities in understanding relationships between visual and textual data through joint embedding spaces. Despite their effectiveness, these models remain vulnerable…

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,…

Large language models (LLMs) have exhibited impressive reasoning abilities on a wide range of complex tasks. However, enhancing these capabilities through post-training remains resource intensive, particularly in terms of data and…

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…

Advanced reasoning in LLMs on challenging domains like mathematical reasoning can be tackled using verifiable rewards based reinforced fine-tuning (ReFT). In standard ReFT frameworks, a behavior model generates multiple completions with…

Large Language Models (LLMs) have achieved human-level fluency in text generation, making it difficult to distinguish between human-written and LLM-generated texts. This poses a growing risk of misuse of LLMs and demands the development of…

Benchmarking outcomes increasingly govern trust, selection, and deployment of LLMs, yet these evaluations remain vulnerable to semantically equivalent adversarial perturbations. Prior work on adversarial robustness in NLP has emphasized…

Fine-tuning pre-trained Vision-Language Models (VLMs) has shown remarkable capabilities in medical image and textual depiction synergy. Nevertheless, many pre-training datasets are restricted by patient privacy concerns, potentially…

The rapid expansion of research on Large Language Model (LLM) safety and robustness has produced a fragmented and oftentimes buggy ecosystem of implementations, datasets, and evaluation methods. This fragmentation makes reproducibility and…

The natural language generation (NLG) module in a task-oriented dialogue system produces user-facing utterances conveying required information. Thus, it is critical for the generated response to be natural and fluent. We propose to…

LLM-powered multi-agent systems can now automate the full research pipeline from ideation to paper writing, but a fundamental question remains: automation for whom? Researchers operate under different resource configurations, hold different…

Existing works show that augmenting the training data of pre-trained language models (PLMs) for classification tasks fine-tuned via parameter-efficient fine-tuning methods (PEFT) using both clean and adversarial examples can enhance their…

Large Language Models (LLMs) have been shown to achieve impressive results for many reasoning-based NLP tasks, suggesting a degree of deductive reasoning capability. However, it remains unclear to which extent LLMs, in both informal and…

Enabling large language models with external tools has become a pivotal strategy for extending their functionality beyond text space. To enhance LLMs' tool-calling abilities, previous approaches primarily rely on supervised fine-tuning…