LMCA_dataset.pdf
andrew.cmu.edu · 7,838 words · saved by 1 readers
N/A
A dataset of rated conceptual arguments Emery Cooper* Caspar Oesterheld* Linh Chi Nguyen Alexander Kastner Ethan Perez 1 Introduction In recent years, the capabilities of large language models (LLMs) have progressed impressively across a wide range of domains. Over the past year or so, so-called reasoning models have made rapid progress on tasks with verifiable feedback, such as coding and math (Jaech et al. 2024; Guo et al. 2025; A. Yang et al. 2025). In light of concerns about the risks of AI development (such as misalignment…
saved by
related reading
- Introducing the Conceptual Reasoning Indexalignment.anthropic.com
- DeepSeek-R1arxiv.org
- As Rocks May Think | Eric Jangevjang.com
- Is AI Reasoning Right for the Wrong Reasons? | Quanta Magazinequantamagazine.org
- the-illusion-of-thinking.pdfml-site.cdn-apple.com
- Thoughts on AI in academiatheinfinitesimal.substack.com
- [2201.11903] Chain of Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
- The Universe from an Intentional Stancecasparoesterheld.com
- Conceptual Reasoning Indexconceptualreasoning.ai
- The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexitymachinelearning.apple.com
- [2406.02061] Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Modelsarxiv.org
- Discovering Language Model Behaviors with Model-Written Evaluations — LessWronglesswrong.com