Tag
This paper evaluates the faithfulness of AquiLLM, an open-weight RAG-LLM system, for scientific research in astronomy, showing strong performance on retrieval tasks but challenges in synthesis.
text2ql is an open-source Python framework for multi-target natural language querying via a language-agnostic intermediate representation, supporting SQL and GraphQL with LLM-backed and deterministic modes, achieving high accuracy on benchmarks.
SemPlan is a benchmark for evaluating structured semantic planning in LLM-based queries over enterprise data, comparing four architectures using a synthetic bilingual dataset of 1,800 cases.