Weekly Showcase Thread October 13, 2024

Hello wonderful people! This thread is the perfect place to share your one off creations without needing a dedicated post or worrying about sharing extra generation data. It’s also a fantastic way to check out what others are creating and get inspired in one place! A few quick reminders: All sub rules still apply make …

GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models

Recent advancements in Large Language Models (LLMs) have sparked interest in their formal reasoning capabilities, particularly in mathematics. The GSM8K benchmark is widely used to assess the mathematical reasoning of models on grade-school-level questions. While the performance of LLMs on GSM8K has significantly improved in recent years, it remains unclear whether their mathematical reasoning capabilities …