2410.05229

N/A

Published as a conference paper at ICLR 2025 GSM-S YMBOLIC : U NDERSTANDING THE L IMITA - TIONS OF M ATHEMATICAL R EASONING IN L ARGE L ANGUAGE M ODELS Iman Mirzadeh1 Keivan Alizadeh1 Hooman Shahrokhi2∗ Oncel Tuzel1 Samy Bengio1 Mehrdad Farajtabar1† 1 Apple 2…

saved by

• Ritvik Varghese

related reading

• [2201.11903] Chain of Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
• the-illusion-of-thinking.pdfml-site.cdn-apple.com
• [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
• Reasoning Models Reason Well, Until They Don'tarxiv.org
• 2310.10631arxiv.org
• [2504.13837] Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?arxiv.org
• 2305.18654arxiv.org
• Language Models can Solve Computer Tasksarxiv.org
• 2308.03958arxiv.org
• [2409.19759] Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMsarxiv.org
• Reasoning in General Domains without Verifiersarxiv.org
• [2502.05209] Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilitiesarxiv.org