相关论文: How Effective Is Constitutional AI in Small LLMs? …

As language models continue to grow larger, the cost of acquiring high-quality training data has increased significantly. Collecting human feedback is both expensive and time-consuming, and manual labels can be noisy, leading to an…

Constitutional AI (CAI) guides LLM behavior using constitutions, but identifying which principles are most effective for model alignment remains an open challenge. We introduce the C3AI framework (\textit{Crafting Constitutions for CAI…

Large language models demonstrate strong performance on mathematical reasoning benchmarks, yet remain surprisingly fragile to meaning-preserving surface perturbations. We systematically evaluate three open-weight LLMs, Mistral-7B,…

Traditional methods for aligning Large Language Models (LLMs), such as Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO), rely on implicit principles, limiting interpretability. Constitutional AI…

Recent advances in Large Language Models (LLMs) have incorporated planning and reasoning capabilities, enabling models to outline steps before execution and provide transparent reasoning paths. This enhancement has reduced errors in…

Recent research has increasingly focused on training large language models (LLMs) using federated learning, known as FedLLM. However, responsible AI (RAI), which aims to ensure safe and trustworthy responses, remains underexplored in this…

Artificial Intelligence (AI) and Large Language Models (LLMs) have rapidly evolved in recent years, showcasing remarkable capabilities in natural language understanding and generation. However, these advancements also raise critical ethical…

Large Language Models have emerged as transformative tools for Security Operations Centers, enabling automated log analysis, phishing triage, and malware explanation; however, deployment in adversarial cybersecurity environments exposes…

With the rapid development of large language models (LLMs), aligning LLMs with human values and societal norms to ensure their reliability and safety has become crucial. Reinforcement learning with human feedback (RLHF) and Constitutional…

Large Language Models (LLMs) have grown increasingly powerful, yet ensuring their decisions remain transparent and trustworthy requires self-consistency -- no contradictions in their internal reasoning. Our study reveals that even on simple…

There is growing consensus that language model (LM) developers should not be the sole deciders of LM behavior, creating a need for methods that enable the broader public to collectively shape the behavior of LM systems that affect them. To…

Recently, large language models (LLMs) have expanded into various domains. However, there remains a need to evaluate how these models perform when prompted with commonplace queries compared to domain-specific queries, which may be useful…

Large language models (LLMs) such as ChatGPT o1, ChatGPT o3, and DeepSeek R1 have shown great potential in solving difficult problems. However, current LLM evaluation benchmarks are limited to one-step interactions. Some of the existing…

Sophisticated instrumentation for AI systems might have indicators that signal misalignment from human values, not unlike a "check engine" light in cars. One such indicator of misalignment is deceptiveness in generated responses. Future AI…

Large Language Models (LLMs) such as OpenAI's GPT-4 and Meta's LLaMA offer a promising approach for scalable personality assessment from open-ended language. However, inferring personality traits remains challenging, and earlier work often…

Several recent works have argued that Large Language Models (LLMs) can be used to tame the data deluge in the cybersecurity field, by improving the automation of Cyber Threat Intelligence (CTI) tasks. This work presents an evaluation…

We investigate the presence of cognitive biases in three large language models (LLMs): GPT-4o, Gemma 2, and Llama 3.1. The study uses 1,500 experiments across nine established cognitive biases to evaluate the models' responses and…

Large language models (LLMs) have demonstrated remarkable capabilities in code-related tasks, particularly in automated program repair. However, the effectiveness of such repairs is highly dependent on the performance of upstream fault…

Can large language models introspect, that is, accurately detect perturbations to their own internal states? We systematically investigate this question using activation steering in Meta-Llama-3.1-8B-Instruct. First, we show that the binary…

Recent advancements in Large Reasoning Models (LRMs), such as OpenAI's o1/o3 and DeepSeek-R1, have demonstrated remarkable performance in specialized reasoning tasks through human-like deliberative thinking and long chain-of-thought…