lab-assistant / evals /testset.jsonl
prarabdhmisra's picture
Deploy lab assistant
f0a602b verified
Raw
History Blame Contribute Delete
2.11 kB
{"question": "What is Spatial-RAG and what problem does it solve?", "expect_doc": "spatial-rag", "in_corpus": true}
{"question": "Tell me about graph retrieval-augmented generation in the lab.", "expect_doc": "grag", "in_corpus": true}
{"question": "How does the lab answer research questions using a citation graph?", "expect_doc": "cg-rag", "in_corpus": true}
{"question": "Which work generates natural-language explanations of GNN predictions?", "expect_doc": "graphnarrator", "in_corpus": true}
{"question": "How does the lab reduce large language model API costs?", "expect_doc": "tools", "in_corpus": true}
{"question": "Representation learning for 3D polyhedra and shapes.", "expect_doc": "polyhedronnet", "in_corpus": true}
{"question": "Forecasting civil unrest from open source indicators.", "expect_doc": "embers", "in_corpus": true}
{"question": "Is Prof. Zhao taking new PhD students and what does he look for?", "expect_doc": "faq", "in_corpus": true}
{"question": "Survey on domain specialization of large language models.", "expect_doc": "domain-specialization-survey", "in_corpus": true}
{"question": "Uncertainty quantification for in-context learning.", "expect_doc": "uq-icl", "in_corpus": true}
{"question": "Federated pruning of large language models.", "expect_doc": "fedspallm", "in_corpus": true}
{"question": "Benchmark for evaluating visual saliency explanations.", "expect_doc": "saliency-bench", "in_corpus": true}
{"question": "Multi-scale Mamba transformer for time series forecasting.", "expect_doc": "sst-mamba-transformer", "in_corpus": true}
{"question": "Continual memory so RAG does not forget.", "expect_doc": "rag-without-forgetting", "in_corpus": true}
{"question": "Agentic geospatial reasoning with scientific concepts.", "expect_doc": "spatial-agent", "in_corpus": true}
{"question": "What is the weather in Atlanta tomorrow afternoon?", "expect_doc": null, "in_corpus": false}
{"question": "Write me a short poem about my pet cat.", "expect_doc": null, "in_corpus": false}
{"question": "What is the stock price of Tesla today?", "expect_doc": null, "in_corpus": false}