AI RESEARCH

Language Models Compare Quantities Using Number-specific and Unit-specific Heuristics

arXiv CS.CL

ArXi:2606.03982v1 Announce Type: new Quantities with measurement units, such as 110 cm and 1.2m, require language models (LMs) to combine a numeral with a symbolic unit scale. Here, we study how LMs compare such quantities in controlled settings spanning several unit systems. We find that accuracy degrades near the comparison boundary, where small changes in value determine the correct answer.