Shared circuits predict whether LLMs generalize across formats in arithmetic reasoning
In many forms of reasoning, including arithmetic reasoning, generalizing across superficial changes in input format is effortless for humans: anyone who can solve 2+5 can also solve'two plus five'. In contrast, LLMs are more brittle to surface variations of the prompts: for example, they solve numeric arithmetic proble...
Andrea Gregor de Varda, Sana Pandey, Peng-Rui Han et al.
· 0 citations