NumeroLogic: Number Encoding for Enhanced LLMs' Numerical Reasoning
This addresses a specific bottleneck in LLMs for tasks requiring numerical reasoning, though it is an incremental improvement over existing methods.
The paper tackled the problem of language models struggling with numerical data and arithmetic by proposing NumeroLogic, a number encoding method that includes digit counts (e.g., '{2:42}'), which improved performance on arithmetic tasks and enhanced language understanding on the MMLU benchmark.
Language models struggle with handling numerical data and performing arithmetic operations. We hypothesize that this limitation can be partially attributed to non-intuitive textual numbers representation. When a digit is read or generated by a causal language model it does not know its place value (e.g. thousands vs. hundreds) until the entire number is processed. To address this issue, we propose a simple adjustment to how numbers are represented by including the count of digits before each number. For instance, instead of "42", we suggest using "{2:42}" as the new format. This approach, which we term NumeroLogic, offers an added advantage in number generation by serving as a Chain of Thought (CoT). By requiring the model to consider the number of digits first, it enhances the reasoning process before generating the actual number. We use arithmetic tasks to demonstrate the effectiveness of the NumeroLogic formatting. We further demonstrate NumeroLogic applicability to general natural language modeling, improving language understanding performance in the MMLU benchmark.