InfinityMath: A scalable instruction-tuning dataset for programmatic mathematical reasoning
A key factor for ai research in mathematical reasoning is that it can further increase models' understanding and problem-solving capabilities ...
Tag: Reasoning
Mutual Self-Playing Reasoning (rStar): A new AI approach that boosts the reasoning ability of small language models during inference without fine-tuning
Large language models (LLMs) have made significant progress in various applications, but they continue to face substantial challenges in complex ...
Google AI introduces CoverBench: a challenging benchmark focused on verifying LM language model results in complex reasoning environments
One of the main challenges in ai research is verifying the accuracy of language model (LM) outputs, especially in contexts ...
ARCLE: A reinforcement learning environment for abstract reasoning challenges
Reinforcement learning (RL) is a specialized branch of artificial intelligence that trains agents to make sequential decisions by rewarding them ...
What is the Chain of Numerical Reasoning in Prompt Engineering?
Introduction Prompt engineering has become essential in the rapidly changing fields of artificial intelligence and natural language processing. Of all ...
How far can transformers go in reasoning? The locality barrier and the inductive notebook
Can Transformers predict new syllogisms by composing established ones? More generally, what kind of targets can these models learn from ...
OpenAI is reportedly working on more advanced AI models capable of reasoning and performing “deep investigations”
A new report from technology/artificial-intelligence/openai-working-new-reasoning-technology-under-code-name-strawberry-2024-07-12/" rel="nofollow noopener" target="_blank" data-ylk="slk:Reuters;elm:context_link;elmt:doNotAffiliate;cpos:1;pos:1;itc:0;sec:content-canvas"> The company says OpenAI is developing technology to bring advanced reasoning ...
The reasoning capabilities of large language models are often overestimated | MIT News
When it comes to artificial intelligence, appearances can be deceptive. The mystery surrounding the inner workings of large language models ...
InternLM2.5-7B-Chat: Open source language models with unmatched reasoning, extensive context handling, and improved tool usage
InternLM has presented its latest advance in large open language models, the InterLM2.5-7B-ChatGGUF is available in GGUF format. This model ...
This AI paper from CMU and Google DeepMind studies the role of synthetic data in improving the mathematical reasoning abilities of LLM students
Large language models (LLMs) face a critical challenge in their training process: the looming shortage of high-quality Internet data. Predictions ...
Recommended.
