Related papers: Cognitive Loop via In-Situ Optimization: Self-Adap…
In artificial intelligence (AI), the complexity of many models and processes surpasses human understanding, making it challenging to determine why a specific prediction is made. This lack of transparency is particularly problematic in…
Research on LLM technologies is rapidly emerging, with most of them employ a 'fast thinking' approach to inference. Most LLMs generate the final result based solely on a single query and LLM's reasoning capabilities. However, with the…
This survey explores recent advancements in reasoning large language models (LLMs) designed to mimic "slow thinking" - a reasoning process inspired by human cognition, as described in Kahneman's Thinking, Fast and Slow. These models, like…
Group Relative Policy Optimization (GRPO) enhances LLM reasoning but often induces overconfidence, where incorrect responses yield lower perplexity than correct ones, degrading relative calibration as described by the Area Under the Curve…
As artificial intelligence (AI) continues to advance, it demonstrates capabilities comparable to human intelligence, with significant potential to transform education and workforce development. This study evaluates OpenAI o1-preview's…
Generative AI tools are increasingly embedded in everyday work and learning, yet their fluency, opacity, and propensity to hallucinate mean that users must critically evaluate AI outputs rather than accept them at face value. The present…
The rapid development of Artificial Intelligence (AI) requires developers and designers of AI systems to focus on the collaboration between humans and machines. AI explanations of system behavior and reasoning are vital for effective…
While large language models (LLMs) with reasoning capabilities are progressing rapidly on high-school math competitions and coding, can they reason effectively through complex, open-ended challenges found in frontier physics research? And…
Recent advancements in large language models have showcased their remarkable generalizability across various domains. However, their reasoning abilities still have significant room for improvement, especially when confronted with scenarios…
Reasoning is a cognitive process of using evidence to reach a sound conclusion. The reasoning capability is essential for large language models (LLMs) to serve as the brain of the artificial general intelligence agent. Recent studies reveal…
Modern LLMs are trained to "think" primarily via explicit text generation, such as chain-of-thought (CoT), which defers reasoning to post-training and under-leverages pre-training data. We present and open-source Ouro, named after the…
Large Language Models (LLMs) often exhibit strong linguistic abilities while remaining unreliable on multi-step reasoning tasks, particularly when deployed without additional training or fine-tuning. In this work, we study inference-time…
We investigate whether modern AI can emulate expert creativity in complex scientific endeavors. We introduce novel methodology that utilizes original research articles published after the AI's training cutoff, ensuring no prior exposure,…
As artificial intelligence (AI) improves, traditional alignment strategies may falter in the face of unpredictable self-improvement, hidden subgoals, and the sheer complexity of intelligent systems. Inspired by contemplative wisdom…
While chain-of-thought (CoT) distillation from advanced large language models (LLMs) has proven effective in general reasoning tasks, it struggles in scientific domains where even advanced models often produce incorrect or superficial…
Large Language Models (LLMs), such as OpenAI's o1-series have demonstrated compelling capabilities for complex reasoning tasks via the extended chain-of-thought (CoT) reasoning mechanism. However, recent studies reveal substantial…
The output quality of large language models (LLMs) can be improved via "reasoning": generating segments of chain-of-thought (CoT) content to further condition the model prior to producing user-facing output. While these chains contain…
When answering a question, humans utilize the information available across different modalities to synthesize a consistent and complete chain of thought (CoT). This process is normally a black box in the case of deep learning models like…
Current approaches for strengthening LLM reasoning tend to introduce a training bias toward human-like reasoning trajectories. In step-wise preference optimization, in particular, dependence on human or higher-capacity model annotations for…
Demonstrations are a powerful way of increasing the transparency of AI policies. Though informative demonstrations may be selected a priori through the machine teaching paradigm, student learning may deviate from the preselected curriculum…