{"kind":"method","resolved_to":{"method":"ROME","origin_arxiv_id":"2206.08343"},"homonyms":[{"origin_arxiv_id":"2206.08343","code_level":null},{"origin_arxiv_id":"2401.10566","code_level":null}],"note_homonyms":"2 distinct methods are named exactly 'ROME'; the answer below is for the most-cited one, attributed to its own paper. Check origin_arxiv_id.","other_spellings":[{"method":"RoMe","origin_arxiv_id":"2203.09183","code_level":null,"ask_with":"have('RoMe')"}],"note_other_spellings":"1 other method(s) differ from 'ROME' only by capitalisation and are NOT the same method. Nothing below is about them; ask for one by its own spelling.","have":"no_code","absence_asserted":"for_this_exact_name_only","tier":"paper_only","fallback":{"method":"ROME","origin_arxiv_id":"2401.10566","paper_title":"ROME: Robust Multi-Modal Density Estimator *","paper_arxiv_id":"2401.10566","verified_implementation":false,"merged_from_nodes":2,"merged_origin_arxiv_ids":["2401.10566","2206.08343"],"tier":"paper_only","what_this_means":"Only the paper is available for this method: no verified implementation, no declared repository, no task resolution."},"code_nearby":[],"note":"No code under the exact name 'ROME' (paper arXiv:2206.08343). Only the paper is available for this method: no verified implementation, no declared repository, no task resolution.","name_competition":{"checked":["method_name","title_prefix","acronym_expansion"],"may_be_wrong_sense":true,"bearers_found":8,"served":{"arxiv_id":"2206.08343","citations":144},"also_named":[{"arxiv_id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","citations":3126,"named_by":["acronym_expansion"],"bearer_name":"Rank-One Model Editing (ROME)","ask_with":"have('2202.05262')"},{"arxiv_id":"2310.19301","title":"ROME: Evaluating Pre-trained Vision-Language Models on Reasoning beyond Visual Common Sense","citations":33,"named_by":["title_prefix"],"bearer_name":"ROME: Evaluating Pre-trained Vision-Language Models on Reasoning beyond Visual Common Sense","ask_with":"have('2310.19301')"},{"arxiv_id":"2203.09183","title":"RoMe: A Robust Metric for Evaluating Natural Language Generation","citations":16,"named_by":["method_name","title_prefix"],"bearer_name":"RoMe","ask_with":"have('2203.09183')"},{"arxiv_id":"2403.00510","title":"ROME: Memorization Insights from Text, Logits and Representation","citations":9,"named_by":["title_prefix"],"bearer_name":"ROME: Memorization Insights from Text, Logits and Representation","ask_with":"have('2403.00510')"},{"arxiv_id":"2011.11233","title":"ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation","citations":5,"named_by":["title_prefix"],"bearer_name":"ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation","ask_with":"have('2011.11233')"}],"verdict":"outranked","note":"'ROME' is ALSO the name of 'Rank-One Model Editing (ROME)', a method in 'Locating and Editing Factual Associations in GPT' (arXiv:2202.05262, 3,126 citations), which is cited FAR more than the paper this answer is about (144). This answer may be about the wrong ROME. If you meant the better-known one, ask again with that entry of `also_named`."},"query":"ROME","cost":"free"}