一个可审查的 LLM 委员会用于多模型研究答案聚合

Computer Science > Computation and Language arXiv:2604.02923 (cs) [Submitted on 3 Apr 2026 (v1), last revised 26 Sep 2026 (this version, v5)] Title:An Inspectable LLM Council for Multi-Model Research Answer Aggregation Authors:Shuai Wu, Xue Li, Yanna Feng, Yufang Li, Zhijun Wang, Ran Wang View a PDF of the paper titled An Inspectable LLM Council for Multi-Model Research Answer Aggregation, by Shuai Wu and 5 other authors View PDF HTML (experimental) Abstract:Long-form research questions often require a single answer that combines details, reconciles conflicting estimates, and retains qualifications spread across several large language model (LLM) outputs. We present an inspectable LLM Council that separates synthesis into two stages: an analyst converts three independent candidate answers into a structured state, and a writer composes the final response from that state. We evaluate the workflow under closed-book conditions on 100 tasks from the Deep Research Accuracy, Completeness, and Objectivity (DRACO) benchmark, retaining 600 final answers, 100 analyst states, and 720 whole-answer judgments across the main and supplementary experiments. Under the primary rubric judge, Council scores 70.98, exceeding GPT and Gemini by 6.18 and 8.34 points; its 0.47-point difference from Claude has a 95% paired interval of $[-0.69,1.61]$. In the full supplementary comparison, Council scores 1.87 points above direct fusion (95% paired interval $[0.33,3.48]$) and covers 51.1% of positive rubric criteria covered by exactly one candidate, compared with 43.7% for direct fusion. On an exploratory 68-task subset with matching returned model labels, direct fusion scores higher, so the full comparison cannot isolate the analyst state's effect. Traced cases show how estimates, provenance qualifications, and selection decisions pass through the saved state into final answers. Comments: Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI) ACM classes: I.2.7; I.2.6; I.2.11 Cite as: arXiv:2604.02923 [cs.CL] (or arXiv:2604.02923v5 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2604.02923 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Shuai Wu [view email] [v1] Fri, 3 Apr 2026 09:40:43 UTC (192 KB) [v2] Tue, 21 Apr 2026 07:07:06 UTC (192 KB) [v3] Sun, 26 Apr 2026 15:11:17 UTC (145 KB) [v4] Sun, 5 Jul 2026 07:16:53 UTC (144 KB) [v5] Sat, 26 Sep 2026 14:21:34 UTC (11,639 KB) Full-text links: Access Paper: View a PDF of the paper titled An Inspectable LLM Council for Multi-Model Research Answer Aggregation, by Shuai Wu and 5 other authors View PDF HTML (experimental) TeX Source view license Ancillary-file links: Ancillary files (details): LICENSE-CODE LICENSE-DATA README.md THIRD-PARTY-NOTICES.md analysis/diagnostics_v3.py analysis/reproduce_v3.py analysis/restore_records.py analysis/supplement.py analysis/test_diagnostics_v3.py analysis/test_reproduce_v3.py analysis/test_supplement_analysis.py data/task_manifest.csv data_records.json data_supplement/analysis/all_calls.csv data_supplement/analysis/costs.csv data_supplement/analysis/coverage.csv data_supplement/analysis/coverage_comparison.pdf data_supplement/analysis/coverage_comparison.png data_supplement/analysis/direction_agreement.csv data_supplement/analysis/length_and_score.pdf data_supplement/analysis/length_and_score.png data_supplement/analysis/length_differences.csv data_supplement/analysis/operations.csv data_supplement/analysis/paired_differences.pdf data_supplement/analysis/paired_differences.png data_supplement/analysis/primary_comparisons.csv data_supplement/analysis/primary_means.csv data_supplement/analysis/returned_label_comparisons.csv data_supplement/analysis/sample.csv data_supplement/analysis/scores.csv data_supplement/analysis/secondary_comparisons.csv data_supplement/analysis/settings.csv data_texts.json data_v3/analysis/configuration_scores.csv data_v3/analysis/coverage_rates.csv data_v3/analysis/dimension_contributions.csv data_v3/analysis/paired_comparisons.csv data_v3/analysis/retained_operations.csv data_v3/analysis/subgroup_scores.csv data_v3/analysis/task_differences.csv data_v3/source/draco_test.jsonl data_v3/stage1_solo_summary.csv data_v3/stage3_scores.csv experiments/records.py experiments/stage1_report.py experiments/stage1_solo.py experiments/stage2_council.py experiments/stage3_judge.py experiments/stage3_report.py experiments/supplement_api.py experiments/supplement_finish.py experiments/supplement_judgments.py experiments/supplement_preflight.py experiments/supplement_run.py experiments/test_stage1_solo.py experiments/test_stage2_council.py experiments/test_stage3_judge.py experiments/test_stage3_report.py experiments/test_supplement.py requirements.txt (55 additional files not shown) Current browse context: cs.CL new | recent | 2026-04 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)