{"id":"W4393147133","doi":"10.1609/aaai.v38i17.29909","title":"Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology","keywords":"Prefix; Task (project management); Computer science; Linguistics; Engineering; Philosophy","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003130178,0.001047768,0.0005537571,0.0002555182,0.0002492877,0.001308343,0.001385629,0.001036668,0.002977217],"category_scores_gemma":[0.04873446,0.0003353941,0.0003307526,0.0002241704,0.0004375886,0.003075887,0.001044211,0.002176337,0.0009699451],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004873689,"about_ca_system_score_gemma":0.001032068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001732315,"about_ca_topic_score_gemma":0.001462329,"domain_scores_codex":[0.9982737,0.0007138216,0.0001373185,0.0005950941,0.0001679704,0.0001120628],"domain_scores_gemma":[0.9699312,0.02346896,0.001603771,0.003223349,0.0008967072,0.0008761222],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.006921419,0.003247762,0.04834213,0.001726635,0.0003970539,0.0005641622,0.001920955,0.05279535,0.2701784,0.002698801,0.003762228,0.6074451],"study_design_scores_gemma":[0.0007537356,0.01123835,0.1023699,0.0002899241,0.001109296,0.001568558,0.00179448,0.6306662,0.2219182,0.0147814,0.01314024,0.0003698205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9148814,0.00081149,0.07363831,0.0003148355,0.0002150825,0.0002247631,0.000309523,0.00565106,0.003953497],"genre_scores_gemma":[0.9662299,0.0001356726,0.0319889,0.0002343331,0.00002679878,0.00007829335,0.0004286357,0.0002024604,0.0006750316],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003130178,"threshold_uncertainty_score":0.01655418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05948428676975581,"score_gpt":0.2982354832972142,"score_spread":0.2387511965274584,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}