相关论文: Capturing AI's Attention: Physics of Repetition, H…

The recently proposed physics-based framework by Huo and Johnson~\cite{huo2024capturing} models the attention mechanism of Large Language Models (LLMs) as an interacting two-body spin system, offering a first-principles explanation for…

Theory based AI research has had a hard time recently and the aim here is to propose a model of what LLMs are actually doing when they impress us with their language skills. The model integrates three established theories of human…

With the rapid evolution of Artificial Intelligence (AI), its potential implications for higher education have become a focal point of interest. This study delves into the capabilities of AI in Physics Education and offers actionable AI…

Large Language Models (LLMs) are rapidly advancing across diverse domains, yet their application in theoretical physics remains inadequate. While current models show competence in mathematical reasoning and code generation, we identify…

Output from generative AI such as ChatGPT, can be repetitive and biased. But more worrying is that this output can mysteriously tip mid-response from good (correct) to bad (misleading or wrong) without the user noticing. In 2024 alone, this…

This theoretical work examines 'hallucinations' in both human cognition and large language models, comparing how each system can produce perceptions or outputs that deviate from reality. Drawing on neuroscience and machine learning…

Theory of Mind is the ability to attribute mental states (beliefs, intents, knowledge, perspectives, etc.) to others and recognize that these mental states may differ from one's own. Theory of Mind is critical to effective communication and…

Large language models (LLMs) show increasingly advanced emergent capabilities and are being incorporated across various societal domains. Understanding their behavior and reasoning abilities therefore holds significant importance. We argue…

Grading assessments is time-consuming and prone to human bias. Students may experience delays in receiving feedback that may not be tailored to their expectations or needs. Harnessing AI in education can be effective for grading…

Language models can be persuaded to abandon factual knowledge. This vulnerability is central to AI safety, but its internal mechanism remains poorly understood. We uncover a compact causal mechanism for persuasion-induced factual errors. A…

The emergence of large language models (LLMs) is a milestone in generative artificial intelligence, achieving significant success in text comprehension and generation tasks. Despite the tremendous success of LLMs in many downstream tasks,…

Large Language Models (LLMs) with hundreds of billions of parameters have transformed the field of machine learning. However, serving these models at inference time is both compute and memory intensive, where a single request can require…

In this work, we present the first general logic of attention. Attention is a powerful cognitive ability that allows agents to focus on potentially complex information, such as logically structured propositions, higher-order beliefs, or…

As students increasingly rely on large language models, hallucinations pose a growing threat to learning. To mitigate this, AI literacy must expand beyond prompt engineering to address how students should detect and respond to LLM…

Attention is a powerful and ubiquitous mechanism for allowing neural models to focus on particular salient pieces of information by taking their weighted average when making predictions. In particular, multi-headed attention is a driving…

Trust in AI is undermined by the fact that there is no science that predicts -- or that can explain to the public -- when an LLM's output (e.g. ChatGPT) is likely to tip mid-response to become wrong, misleading, irrelevant or dangerous.…

Artificial intelligence's (AI) progress holds great promise in tackling pressing societal concerns such as health and climate. Large Language Models (LLM) and the derived chatbots, like ChatGPT, have highly improved the natural language…

Large Language Models (LLMs) are claimed to be capable of Natural Language Inference (NLI), necessary for applied tasks like question answering and summarization. We present a series of behavioral studies on several LLM families (LLaMA,…

Assessments of algorithmic bias in large language models (LLMs) are generally catered to uncovering systemic discrimination based on protected characteristics such as sex and ethnicity. However, there are over 180 documented cognitive…

Artificial intelligence (AI) tools such as large language models (LLMs) are already altering student learning. Unlike previous technologies, LLMs can independently solve problems regardless of student understanding, yet are not always…