List-aware Reranking-Truncation Joint Model for Search and Retrieval-augmented Generation

The results of information retrieval (IR) are usually presented in the form of a ranked list of candidate documents, such as web search for humans and retrieval-augmented generation for large language models (LLMs). List-aware retrieval aims to capture the list-level contextual features to return a better list, mainly including reranking and truncation. Reranking finely re-scores the documents in the list. Truncation dynamically determines the cut-off point of the ranked list to achieve the trade-off between overall relevance and avoiding misinformation …

cs.ai cs.cl cs.ir documents features form humans information language language models large language large language models list llms retrieval retrieval-augmented search web web search