{"url":"/dataset/catbabi-lm-mode","name":"catbAbI LM-mode","full_name":"concatenated-bAbI","description_markdown":"We aim to improve the bAbI benchmark as a means of developing intelligent dialogue agents. To this end, we propose concatenated-bAbI (catbAbI): an infinite sequence of bAbI stories. catbAbI is generated from the bAbI dataset and during training, a random sample/story from any task is drawn without replacement and concatenated to the ongoing story. The preprocessig for catbAbI addresses several issues: it removes the supporting facts, leaves the questions embedded in the story, inserts the correct answer after the question mark, and tokenises the full sample into a single sequence of words. As such, catbAbI is designed to be trained in an autoregressive way and analogous to closed-book question answering.\r\n\r\ncatbAbI models can be trained in two different ways: language modelling mode (LM-mode) or question-answering mode (QA-mode). In LM-mode, the catbAbI models are trained like autoregressive word-level language models. In QA-mode, the catbAbI models are only trained to predict the tokens that are answers to questions—making it more similar to regular bAbI. QA-mode is simply implemented by masking out losses on non-answer predictions. In both training modes, the model performance is solely measured by its accuracy and perplexity when answering the questions.","description_withheld":null,"homepage":"https://github.com/ischlag/Fast-Weight-Memory-public","introduced_date":"2020-11-16","introduced_date_note":null,"introduced_by":{"paper":"/paper/learning-associative-inference-using-fast-1","title":"Learning Associative Inference Using Fast Weight Memory","first_author":"Imanol Schlag","url":null},"license":{"name":"MIT","url":"https://github.com/ischlag/Fast-Weight-Memory-public/blob/main/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["catbAbI QA-mode","catbAbI LM-mode"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-catbabi-lm-mode","task":"Question Answering","dataset_variant":"catbAbI LM-mode","rows":4,"metrics":["Accuracy (mean)"],"first_row_in_archive_order":{"model":"Fast Weight Memory","paper":"/paper/learning-associative-inference-using-fast-1","metrics":{"Accuracy (mean)":"93.04%"},"code_links":[{"title":"ischlag/Fast-Weight-Memory-public","url":"https://github.com/ischlag/Fast-Weight-Memory-public"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/learning-associative-inference-using-fast-1","title":"Learning Associative Inference Using Fast Weight Memory","date":"2020-11-16","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}