Menu

Why Semantic Similarity Can Give AI the Exact Opposite Answer
📰

Why Semantic Similarity Can Give AI the Exact Opposite Answer

Reading 0:00
15s threshold

TL;DR: An embedding's similarity score measures how much two texts share in topic and wording, and a negation is a one-word edit. I wrote 40 invented policy facts and tested six open embedding models. On every model, "Which plan doesn't cover X?" scored closer to "Which plan covers X?" than a plain rewording of the same question did, for 77.5–100% of the items. At a common semantic-cache cut-off (similarity 0.90, RedisVL's default), one model would serve the cached answer to 97.5% of the opposite questions and to 7.5% of the genuine rewordings. In retrieval, models found the "covered" chunk almost every time and the "not covered" chunk between 27.5% and 92.5% of the time. Adding BM25 through rank fusion made five of the six worse. Dropping English stop words, which removes "not", took BM25 to a coin flip. Re-ranking the top ten with a small cross-encoder took every model to 97.5% or better on the negated questions.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.