Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2304.09542/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:27:26 GMTIs ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents — HN submissionhttps://news.ycombinator.com/item?id=40646164urn:hackerpapers:submission:2304.09542:40646164Tue, 11 Jun 2024 13:50:04 GMT<p>Show HN: rerank-ts – TypeScript Library for Re-Ranking Search Results with LLMs</p><p>Hi HN, we are announcing a TypeScript library for re-ranking search results from vector databases or from full text search indexes. Re-Ranking is a very important step in retrieval for building RAG applications. It almost immediately improves accuracy of LLM&#x27;s response synthesis as you are able to feed in much more accurate and relevant context. Why? Because while semantic or full text search systems are designed to be fast and fetch semantically or lexically close document chunks, they don&#x27;t rank the chunks based on the intent of the user&#x27;s query. This is where a re-ranker comes in. Why did…</p><p>1 point; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2304.09542/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CL