Do LLM Debates Repeat Arguments Differently Across Languages?

Abstract

LLM debate is usually evaluated by final answers, but transcripts also reveal whether later turns develop new argumentative content or return to earlier claims in new wording. We study this process with \textit{prior-argument similarity}, an aggregate diagnostic comparing extracted argument units with earlier units in the same debate. In controlled eight-turn debates over 71 motions, six languages, and four model agents, Chinese is the only tested language with a consistently positive gap relative to English across three multilingual embedding models. The gap persists across agents, turn positions, regression adjustment, metric variants, extraction-length controls, a second-extractor subset, and cross-encoder tail rescoring. Manual calibration shows weak item-level alignment but a high-similarity tail enriched for substantive repetition. A diversity-aware prompt lowers prior-argument similarity across languages, yet does not significantly narrow the Chinese--English gap. These findings suggest that multilingual debate evaluation should measure argumentative development over time and report mitigation effects in both average and gap terms.