Cites: Why Can't Transformers Learn Multiplication? Reverse-Engineering Reveals Long-Range Dependency Pitfalls

6 citation edges inside this catalog. A title match is weaker evidence than an identifier match. Zero entries does not mean no citations on the web.

• Progress measures for grokking via mechanistic interpretability
  arxiv:2301.05217 · evidence: id
• Physics of Language Models: Part 3.1, Knowledge Storage and Extraction
  arxiv:2309.14316 · evidence: id
• From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
  arxiv:2405.14838 · evidence: id
• Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process
  arxiv:2407.20311 · evidence: id
• Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics
  arxiv:2410.21272 · evidence: id
• Language Models Use Trigonometry to Do Addition
  arxiv:2502.00873 · evidence: id