S Banerjee (@SB434223)RAG에서 임베딩 품질만으로는 충분하지 않으며, 데이터가 커질수록 검색 공간이 조밀해져 ‘거의 관련 있는’ 문서가 늘고 recall이 떨어진다는 점을 강조한다. 따라서 대규모 RAG에서는 reranking 같은 후처리와 검색 설계가 중요하다는 기술적 인사이트를 제시한다.https://x.com/SB434223/status/2052648564321595428#rag #embedding #reranking #retrieval #llm
Related
In human-AI teams where the AI is advanced, "exotic team dynamics" emerge. One example is superposition roles - AI simul...
In human-AI teams where the AI is advanced, "exotic team dynamics" emerge. One example is superposition roles - AI simultaneously performing multiple roles. Navigating them is esse...
Google Search Now Connects to Instacart, Canva and YouTube MusicGoogle is expanding AI Mode in Search, allowing users to...
Google Search Now Connects to Instacart, Canva and YouTube MusicGoogle is expanding AI Mode in Search, allowing users to connect apps to improve search results and "get more done."...
MANAGING SYMPTOMS. NOT SEEKING #ENLIGHTENMENTPeople sometimes mistake me for someone spiritual. I am not. I am practical...
MANAGING SYMPTOMS. NOT SEEKING #ENLIGHTENMENTPeople sometimes mistake me for someone spiritual. I am not. I am practical.I #breathe consciously because it hurts when I do not. I fa...