{"paper":{"title":"Active Learning of Approximate LLM Ranking for Energy-Efficient Retrieval of Long Queries","arxiv_id":"2611.16488","primary_cat":"cs.IR","submitted_at":"2026-11-12T08:59:23+00:00","version_compiled":"v1"},"notice":"Every quoted sentence is the authors' text from the arXiv listing abstract. Labels and probabilities are the outputs of classifier-1.13.0 on the question bank abstract-p1-20260923, exactly as returned. No sentence in this record was written by a language model.","schema":"pith.compiled-record/v0","status":"compiled","abstract":{"source":"arXiv listing abstract v1","sentences":[{"i":0,"p":1.0,"id":"s0","own":false,"role":"background","text":"Search engines and Large Language Models (LLMs) offer complementary strengths for document retrieval: lexical retrievers which rely on keyword matching are fast and energy-efficient, whereas LLMs capture semantic meaning and excel at interpreting long, context-rich queries.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.06,"main_claim_p":0.03,"quantitative":true,"quantitative_p":0.58,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":1.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.88,"id":"s1","own":false,"role":"background","text":"However, this comes at a cost that is computationally and energetically prohibitive.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.09,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.08,"method":0.0,"result":0.0,"background":0.88,"limitation":0.04,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.77,"id":"s2","own":true,"role":"contribution","text":"We propose the LLM Active Approximation Model (LAAM), a hybrid retrieval framework that introduces a lightweight learned predictor which serves as an intermediary between semantic retrieval and LLM retrieval.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.84,"main_claim_p":0.07,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.23,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.77,"interpretation":0.0}},{"i":3,"p":0.99,"id":"s3","own":true,"role":"method","text":"LAAM is refined through an active learning loop where an LLM labels a small number of documents.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.86,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.15,"role_probabilities":{"gap":0.0,"method":0.99,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.0}},{"i":4,"p":0.49,"id":"s4","own":true,"role":"result","text":"By concentrating LLM evaluations on the most informative documents, the framework substantially reduces inference cost while preserving retrieval effectiveness.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.79,"main_claim_p":0.26,"quantitative":false,"quantitative_p":0.1,"role_probabilities":{"gap":0.0,"method":0.17,"result":0.49,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.18,"interpretation":0.16}},{"i":5,"p":0.99,"id":"s5","own":true,"role":"method","text":"We evaluate the proposed framework on TREC Robust 2004 using Lucene with BM25 retrieval and DeepSeek v3 as the LLM, under three levels of query verbosity.","hedge":{"p":0.96,"label":"asserted"},"own_p":0.95,"main_claim_p":0.03,"quantitative":true,"quantitative_p":0.52,"role_probabilities":{"gap":0.0,"method":0.99,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.0}},{"i":6,"p":1.0,"id":"s6","own":true,"role":"result","text":"For verbose queries, LAAM achieves 87% of average P@10 achieved by DeepSeek's reranking (0.459 vs. 0.526), while requiring only 3.3% of the per-query energy consumption.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.97,"main_claim_p":0.13,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":7,"p":1.0,"id":"s7","own":true,"role":"result","text":"LAAM is statistically significantly better than BM25 and is indistinguishable from DeepSeek on average precision, though not on MAP (Friedman test, P<0.05 with post-hoc testing).","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.09,"quantitative":true,"quantitative_p":0.98,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":8,"p":0.98,"id":"s8","own":true,"role":"interpretation","text":"Overall, our results demonstrate that selectively approximating LLM relevance judgments through active learning enables retrieval accuracy to be controlled directly through the evaluation (and consequently energy) budget.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.83,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.02,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.98}},{"i":9,"p":0.96,"id":"s9","own":true,"role":"interpretation","text":"Rather than committing to either inexpensive (and less accurate) lexical retrieval or exhaustive (and expensive) LLM reranking, our framework exposes a continuous spectrum of operating points along the energy--accuracy curve, allowing practitioners to select how to trade retrieval quality with computational budget.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.74,"main_claim_p":0.39,"quantitative":false,"quantitative_p":0.13,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.04,"interpretation":0.96}}]},"compiled":{"main_claim":{"p":0.95,"text":"Overall, our results demonstrate that selectively approximating LLM relevance judgments through active learning enables retrieval accuracy to be controlled directly through the evaluation (and consequently energy) budget.","location":"abstract s8","hedge_strength":{"p":1.0,"label":"asserted"}},"provenance":{"route":{"via":"TypeSafe API","model":"classifier-1.13.0","endpoint":"https://api.typesafe.ai/v1/systemone","provider":"TypeSafe"},"packing":"one request per paper","requests":1,"input_tokens":7821,"cost_usd_reported":0.0},"compiled_at":"2026-11-13","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.04,"states_limitation":0.6,"human_participants":0.03,"controlled_comparison":0.94,"randomized_assignment":0.02,"states_quantitative_result":0.99,"compares_with_prior_results":0.97,"mentions_code_or_data_availability":0.03},"evidential_basis":{"p":0.98,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.0,"observation_or_experiment":0.98,"simulation_or_computation":0.02}},"contribution_type":{"p":1.0,"value":"method or tool","probabilities":{"review":0.0,"method_or_tool":1.0,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":1.0,"text":"We propose the LLM Active Approximation Model (LAAM), a hybrid retrieval framework that introduces a lightweight learned predictor which serves as an intermediary between semantic retrieval and LLM retrieval.","location":"abstract s2"}},"coverage":{"tier":"abstract","levels_run":["P abstract"],"not_examined":["full text","figures and tables","references and citing sentences","relations to other papers"],"sources_read":["arXiv listing abstract v1"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":10,"sentences_in_abstract":10},"measured_accuracy":{"url":"https://pith.science/accuracy","measured_on":"2026-10-02","method":"two independent model families labelled a fresh random sample blind; the figure is how often the published label matches their consensus","sentence_role_agreement":0.92,"main_claim_agreement":0.908,"typed_citation_agreement":0.933,"typed_citation_agreement_95_interval":[0.917,0.945],"review_comments_accurate":0.758,"review_comments_accurate_95_interval":[0.684,0.82],"review_caught_admitted_error_found_or_related":0.448,"review_comments_judged":{"judged_by":["gpt-5.6-luna","grok-4.7"],"judged_against":"Pith's own text copy of each paper: text extracted from the PDF, the first 90,000 characters","measured_on":"2026-10-04","accurate":113,"decided":149,"sampled_reviews":200,"split_by_lane":false,"by_lane":"https://pith.science/accuracy#by-lane"}}}