{"url":"/task/retrieval-augmented-few-shot-in-context-audio","name":"Retrieval-augmented Few-shot In-context Audio Captioning","slug":"retrieval-augmented-few-shot-in-context-audio","description_markdown":"Retrieval-augmented few-shot in-context audio captioning is a specialized approach within the broader domain of audio captioning. This technique leverages the principles of few-shot in-context learning, akin to those used in LLMs, to generate textual descriptions for audio content without training on the dataset. Instead, during inference, the model utilizes a few-shot retrieval method where a few selected examples from the training data are presented in-context. This allows the model to generate accurate and contextually relevant captions based on limited input.","categories":[{"name":"Audio","url":"/area/audio"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":5,"papers_with_code":5,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/retrieval-augmented-few-shot-in-context-audio","slug":"retrieval-augmented-few-shot-in-context-audio","dataset":"AudioCaps","dataset_url":"/dataset/audiocaps","rows_in_archive":5,"metrics":["CIDEr"],"first_row_in_archive_order":{"model":"Audio Flamingo (4-shot)","paper_title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","paper_url":"/paper/audio-flamingo-a-novel-audio-language-model","paper_date":"2024-02-02","arxiv_id":"2402.01831","code_links":[{"title":"NVIDIA/audio-flamingo","url":"https://github.com/NVIDIA/audio-flamingo"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}}}],"datasets":[{"url":"/dataset/audiocaps","name":"AudioCaps","full_name":"","num_papers_in_archive":279}],"subtasks":[],"parent_tasks":[{"url":"/task/audio-captioning","name":"Audio captioning"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":5,"of":5,"tagged_in_all":5,"items":[{"url":"/paper/audio-flamingo-a-novel-audio-language-model","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","date":"2024-02-02","arxiv_id":"2402.01831","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/recap-retrieval-augmented-audio-captioning","title":"RECAP: Retrieval-Augmented Audio Captioning","date":"2023-09-18","arxiv_id":"2309.09836","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_unverified":3,"n_pointer_only":8}},{"url":"/paper/prefix-tuning-for-automated-audio-captioning","title":"Prefix tuning for automated audio captioning","date":"2023-03-30","arxiv_id":"2303.17489","repositories_listed":1,"syntology":null},{"url":"/paper/automated-audio-captioning-by-fine-tuning","title":"AUTOMATED AUDIO CAPTIONING BY FINE-TUNING BART WITH AUDIOSET TAGS","date":"2021-11-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/audio-captioning-transformer","title":"Audio Captioning Transformer","date":"2021-07-21","arxiv_id":"2107.09817","repositories_listed":1,"syntology":null}],"syntology_records":2,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}