{"id":"W4415428029","doi":"10.3233/faia251254","title":"LLMs for Resource Allocation: A Participatory Budgeting Approach to Inferring Preferences","year":2025,"lang":"","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Auction Theory and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Benchmark (surveying); Task (project management); Resource allocation; Resource (disambiguation); Resource management (computing); Citizen journalism","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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.002963177,0.0006373757,0.0009195881,0.001175731,0.001532008,0.0005658148,0.001470904,0.0005525966,0.00009369889],"category_scores_gemma":[0.0007265708,0.0006658777,0.0002630369,0.001255177,0.0009115889,0.0002984194,0.0003886176,0.0006361682,0.0001537479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001540171,"about_ca_system_score_gemma":0.0003046882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002222776,"about_ca_topic_score_gemma":0.00003848331,"domain_scores_codex":[0.9939114,0.0001478796,0.002496965,0.002099759,0.0006548368,0.0006891341],"domain_scores_gemma":[0.995675,0.001333098,0.0007232141,0.001292847,0.0005592062,0.0004166134],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006536722,0.0001417529,0.00007308642,0.0000514522,0.00003438147,1.016649e-7,0.0009020988,0.003948216,0.00002221918,0.587969,0.001468265,0.4053241],"study_design_scores_gemma":[0.00003754965,0.00005653419,0.00001795749,0.0001682528,0.00009093144,0.000001316218,0.007909594,0.01900572,0.0006984458,0.6108522,0.3606484,0.0005131221],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001041009,0.0008762979,0.9137937,0.001566355,0.0003632596,0.004514357,0.0001839125,0.00007487204,0.07852317],"genre_scores_gemma":[0.6328417,0.00172192,0.2305004,0.002434958,0.002429219,0.0335932,0.0004175338,0.000205136,0.09585596],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6832933,"threshold_uncertainty_score":0.9997678,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2067607473149082,"score_gpt":0.3818599941867186,"score_spread":0.1750992468718104,"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."}}