{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002107226,0.0002065287,0.0002737118,0.0001219463,0.0002806323,0.00033358,0.001282187,0.0000772733,0.00000283948],"category_scores_gemma":[0.001595576,0.0001280965,0.0002370254,0.0006831424,0.0001718196,0.0004443465,0.0002331378,0.0003153489,0.00001166016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006139854,"about_ca_system_score_gemma":0.0001378499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005587644,"about_ca_topic_score_gemma":0.000002042452,"domain_scores_codex":[0.9981774,0.00007242379,0.0005548297,0.0004677156,0.0004425226,0.0002851115],"domain_scores_gemma":[0.9979309,0.001015013,0.0003007428,0.0002355392,0.0004739871,0.00004385996],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001810482,0.00002292366,0.000225385,0.0004599954,0.00003898566,1.868099e-7,0.00142074,0.0004154795,0.1224273,0.8554858,0.00000949178,0.01947556],"study_design_scores_gemma":[0.00002913569,0.0002752551,0.0004443667,0.003820866,0.0000333393,0.000006066481,0.0004738226,0.08955871,0.7223067,0.1825449,0.0003156716,0.0001911314],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7477295,0.0001685779,0.2434761,0.0009290181,0.003107608,0.001848555,0.000006227649,0.0002034667,0.00253101],"genre_scores_gemma":[0.9975705,0.000004955779,0.001965839,0.00001937352,0.0001141339,0.0001139038,3.869064e-7,0.00001665853,0.0001942891],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6729409,"threshold_uncertainty_score":0.5223623,"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."}}