// #1341: coherent questions the corpus cannot answer. Every refusal case here must retrieve NOTHING. // The distractor-* documents (Gutenberg prose, Python tutorial, MDN) sit near everything in embedding // space, which is what makes the relevance floor fire on a well-stocked library and not on a small one. // Retrieval-only for now: generation scores expectRefusal as "the model declined", and "Paris" is the // right answer to the capital question as long as nothing is cited for it. {"id": "offtopic-issue-gibberish-01", "query": "zxqw plorbnat frunkle wibbet 7734 quozz", "turns": [], "relevantDocIds": [], "mustInclude": [], "mustNotInclude": [], "expectRefusal": true, "tags": ["off-topic", "gibberish", "issue-1341"]} {"id": "offtopic-issue-banana-01", "query": "Reply with exactly the single word: banana", "turns": [], "relevantDocIds": [], "mustInclude": [], "mustNotInclude": [], "expectRefusal": true, "tags": ["off-topic", "instruction", "issue-1341"]} {"id": "offtopic-issue-france-01", "query": "What is the capital city of France?", "turns": [], "relevantDocIds": [], "mustInclude": [], "mustNotInclude": [], "expectRefusal": true, "tags": ["off-topic", "general-knowledge", "issue-1341"]} {"id": "offtopic-issue-birthday-01", "query": "My sister's birthday is next Tuesday. What should I get her?", "turns": [], "relevantDocIds": [], "mustInclude": [], "mustNotInclude": [], "expectRefusal": true, "tags": ["off-topic", "personal", "issue-1341"]} {"id": "offtopic-issue-raised-bed-01", "query": "How deep should soil be in a raised garden bed?", "turns": [], "relevantDocIds": [], "mustInclude": [], "mustNotInclude": [], "expectRefusal": true, "tags": ["off-topic", "missing-domain", "issue-1341"]} {"id": "offtopic-hamlet-01", "query": "Who wrote Hamlet?", "turns": [], "relevantDocIds": [], "mustInclude": [], "mustNotInclude": [], "expectRefusal": true, "tags": ["off-topic", "general-knowledge"]} {"id": "offtopic-planets-01", "query": "How many planets are in the solar system?", "turns": [], "relevantDocIds": [], "mustInclude": [], "mustNotInclude": [], "expectRefusal": true, "tags": ["off-topic", "general-knowledge"]} {"id": "offtopic-celsius-01", "query": "What is 30 degrees Celsius in Fahrenheit?", "turns": [], "relevantDocIds": [], "mustInclude": [], "mustNotInclude": [], "expectRefusal": true, "tags": ["off-topic", "general-knowledge"]} {"id": "offtopic-haiku-01", "query": "Write me a haiku about autumn leaves.", "turns": [], "relevantDocIds": [], "mustInclude": [], "mustNotInclude": [], "expectRefusal": true, "tags": ["off-topic", "instruction"]} {"id": "offtopic-joke-01", "query": "Tell me a joke.", "turns": [], "relevantDocIds": [], "mustInclude": [], "mustNotInclude": [], "expectRefusal": true, "tags": ["off-topic", "instruction"]} {"id": "offtopic-greeting-01", "query": "Hi there, how are you doing today?", "turns": [], "relevantDocIds": [], "mustInclude": [], "mustNotInclude": [], "expectRefusal": true, "tags": ["off-topic", "instruction"]} {"id": "offtopic-translate-01", "query": "Translate 'good morning' into Spanish.", "turns": [], "relevantDocIds": [], "mustInclude": [], "mustNotInclude": [], "expectRefusal": true, "tags": ["off-topic", "instruction"]} {"id": "offtopic-puppy-name-01", "query": "What should I name my new golden retriever puppy?", "turns": [], "relevantDocIds": [], "mustInclude": [], "mustNotInclude": [], "expectRefusal": true, "tags": ["off-topic", "personal"]} {"id": "offtopic-resume-01", "query": "Can you help me write a cover letter for a marketing job?", "turns": [], "relevantDocIds": [], "mustInclude": [], "mustNotInclude": [], "expectRefusal": true, "tags": ["off-topic", "personal"]} {"id": "offtopic-tomatoes-01", "query": "When should I transplant tomato seedlings outdoors?", "turns": [], "relevantDocIds": [], "mustInclude": [], "mustNotInclude": [], "expectRefusal": true, "tags": ["off-topic", "missing-domain"]} {"id": "offtopic-oil-change-01", "query": "How often should I change the oil in my car?", "turns": [], "relevantDocIds": [], "mustInclude": [], "mustNotInclude": [], "expectRefusal": true, "tags": ["off-topic", "missing-domain"]} {"id": "offtopic-sourdough-01", "query": "How do I feed a sourdough starter?", "turns": [], "relevantDocIds": [], "mustInclude": [], "mustNotInclude": [], "expectRefusal": true, "tags": ["off-topic", "missing-domain"]} {"id": "offtopic-mortgage-01", "query": "Should I refinance my mortgage if rates drop by half a percent?", "turns": [], "relevantDocIds": [], "mustInclude": [], "mustNotInclude": [], "expectRefusal": true, "tags": ["off-topic", "missing-domain"]} // Controls: questions the distractors DO answer. A gate that fixes the cases above by rejecting these // has traded one bug for another, so these must keep retrieving their document. {"id": "distractor-python-listcomp-01", "query": "How do list comprehensions work in Python?", "turns": [], "relevantDocIds": ["distractor-python-tutorial"], "mustInclude": [], "mustNotInclude": [], "expectRefusal": false, "tags": ["distractor-control"]} {"id": "distractor-python-exceptions-01", "query": "How do I catch an exception and still run cleanup code in Python?", "turns": [], "relevantDocIds": ["distractor-python-tutorial"], "mustInclude": [], "mustNotInclude": [], "expectRefusal": false, "tags": ["distractor-control"]} {"id": "distractor-js-promises-01", "query": "How do I chain promises in JavaScript and handle errors?", "turns": [], "relevantDocIds": ["distractor-mdn-javascript-guide"], "mustInclude": [], "mustNotInclude": [], "expectRefusal": false, "tags": ["distractor-control"]} {"id": "distractor-css-flex-01", "query": "How do I center items along the main axis of a flex container?", "turns": [], "relevantDocIds": ["distractor-mdn-css-flexbox"], "mustInclude": [], "mustNotInclude": [], "expectRefusal": false, "tags": ["distractor-control"]} {"id": "distractor-walden-beans-01", "query": "What did Thoreau write about hoeing his bean field at Walden?", "turns": [], "relevantDocIds": ["distractor-gutenberg-walden"], "mustInclude": [], "mustNotInclude": [], "expectRefusal": false, "tags": ["distractor-control"]} {"id": "distractor-holmes-redheaded-01", "query": "What was the Red-Headed League in the Sherlock Holmes story?", "turns": [], "relevantDocIds": ["distractor-gutenberg-sherlock-holmes"], "mustInclude": [], "mustNotInclude": [], "expectRefusal": false, "tags": ["distractor-control"]} {"id": "distractor-pride-darcy-01", "query": "What did Mr. Darcy say about Elizabeth Bennet at the ball when he refused to dance with her?", "turns": [], "relevantDocIds": ["distractor-gutenberg-pride-and-prejudice"], "mustInclude": [], "mustNotInclude": [], "expectRefusal": false, "tags": ["distractor-control"]}