{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/is-a-prompt-and-a-few-samples-all-you-need","title":"The Parrot Dilemma: Human-Labeled vs. LLM-augmented Data in Classification Tasks","arxiv_id":"2304.13861","date":"2023-04-26","proceeding":null,"authors":["Anders Giovanni Møller","Jacob Aarup Dalsgaard","Arianna Pera","Luca Maria Aiello"],"abstract":"In the realm of Computational Social Science (CSS), practitioners often navigate complex, low-resource domains and face the costly and time-intensive challenges of acquiring and annotating data. We aim to establish a set of guidelines to address such challenges, comparing the use of human-labeled data with synthetically generated data from GPT-4 and Llama-2 in ten distinct CSS classification tasks of varying complexity. Additionally, we examine the impact of training data sizes on performance. Our findings reveal that models trained on human-labeled data consistently exhibit superior or comparable performance compared to their synthetically augmented counterparts. Nevertheless, synthetic augmentation proves beneficial, particularly in improving performance on rare classes within multi-class tasks. Furthermore, we leverage GPT-4 and Llama-2 for zero-shot classification and find that, while they generally display strong performance, they often fall short when compared to specialized classifiers trained on moderately sized training sets.","url_abs":"https://arxiv.org/abs/2304.13861v2","url_pdf":"https://arxiv.org/pdf/2304.13861v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"is-a-prompt-and-a-few-samples-all-you-need","repo_url":"https://github.com/andersgiovanni/worker_vs_gpt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"is-a-prompt-and-a-few-samples-all-you-need","repo_url":"https://github.com/AGMoller/worker_vs_gpt","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"navigate","task_name":"Navigate"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"},{"task_slug":null,"task_name":"zero-shot-classification"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"base","method_name":"BASE"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"test","method_name":"Test"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2304.13861","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.13861"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AGMoller/worker_vs_gpt","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/andersgiovanni/worker_vs_gpt","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"d029f1fd085ec91e","entry":"parse_llama_output","repo":"AGMoller/worker_vs_gpt","repo_kind":"official","path":"src/worker_vs_gpt/utils.py","file_url":"https://github.com/AGMoller/worker_vs_gpt/blob/HEAD/src/worker_vs_gpt/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d029f1fd085ec91e"}},{"code_sha256_prefix":"576cc3f3886cae51","entry":"parse_output","repo":"AGMoller/worker_vs_gpt","repo_kind":"official","path":"src/worker_vs_gpt/utils.py","file_url":"https://github.com/AGMoller/worker_vs_gpt/blob/HEAD/src/worker_vs_gpt/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"576cc3f3886cae51"}},{"code_sha256_prefix":"45c45b78efe4b52b","entry":"query","repo":"AGMoller/worker_vs_gpt","repo_kind":"official","path":"src/worker_vs_gpt/hf_inference.py","file_url":"https://github.com/AGMoller/worker_vs_gpt/blob/HEAD/src/worker_vs_gpt/hf_inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"45c45b78efe4b52b"}},{"code_sha256_prefix":"dd66b2a0f811f16d","entry":"read_json","repo":"AGMoller/worker_vs_gpt","repo_kind":"official","path":"src/worker_vs_gpt/utils.py","file_url":"https://github.com/AGMoller/worker_vs_gpt/blob/HEAD/src/worker_vs_gpt/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dd66b2a0f811f16d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}