Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Question Answering

ArXi:2605.27164v1 Announce Type: new Retrieval-Augmented Generation (RAG) systems for question answering typically retrieve evidence by semantic similarity between the query and document chunks. While effective for unstructured text, this approach is less reliable on semi-structured corpora where answering may require exact filtering, aggregation, or exhaustive retrieval over structured attributes across multiple documents. Symbolic approaches such operations, but they are often brittle on noisy natural-language corpora.