{"id":"W4392669730","doi":"10.18653/v1/2023.eval4nlp-1.16","title":"Reference-Free Summarization Evaluation with Large Language Models","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; National Research Council Canada","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Automatic summarization; Computer science; Natural language processing; Multi-document summarization; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005387756,0.00006295659,0.00005920824,0.00009487847,0.00006268938,0.00007812502,0.0004712007,0.00003437321,0.0000427895],"category_scores_gemma":[0.00003519054,0.00004863908,0.0000107683,0.0004544847,0.000004789507,0.0005435232,0.0002056347,0.00005206894,0.0000772475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002816382,"about_ca_system_score_gemma":0.00006573884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006627884,"about_ca_topic_score_gemma":0.0001835397,"domain_scores_codex":[0.9989901,0.0000441183,0.0001008054,0.0002499334,0.0004380248,0.0001770656],"domain_scores_gemma":[0.9991577,0.00002437616,0.00003012009,0.0006491485,0.0001046037,0.00003400305],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003974938,0.00002566491,0.0004411213,0.00001197098,0.00001154483,0.000007903469,0.003058813,0.08119846,0.0003630002,0.8584452,0.002269499,0.0541629],"study_design_scores_gemma":[0.0003253901,0.00001523833,0.0003756873,0.000007177198,0.000003330899,9.779772e-7,0.0001145593,0.9764711,0.0001886886,0.02229967,0.0001235571,0.00007457266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0333547,0.00001562927,0.9328963,0.0005486598,0.00006460325,0.0001496056,0.000001865412,0.0004738385,0.03249479],"genre_scores_gemma":[0.9593134,0.000004566944,0.03850942,0.0001532874,0.00002993399,0.00002526602,0.00003263819,0.000006082355,0.001925385],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9259587,"threshold_uncertainty_score":0.1983444,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06768538163856708,"score_gpt":0.2967039691196833,"score_spread":0.2290185874811162,"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."}}