{"paper":{"title":"From Textual Columns to Query Plans: A Unified Relational-Semantic Execution Framework for Hybrid Query Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"OmniTQA turns LLM semantic reasoning into an optimizable operator inside relational query plans to process mixed structured and textual tables more accurately and at lower cost than pure symbolic or pure semantic methods.","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Estevam Hruschka, Nikita Bhutani, Nima Shahbazi, Seiji Maekawa","submitted_at":"2026-04-02T18:16:11Z","abstract_excerpt":"Real-world table question answering often involves hybrid schemas in which some query-relevant information is explicit in relational columns, while other attributes, predicates, or join conditions are only implicit in free-form text. Existing systems struggle with this setting: Text-to-SQL methods scale to large and multi-table databases but require fully structured schemas, whereas direct LLM-based methods can interpret textual content but are costly and unreliable when applied to large databases. We present OmniTQA, a unified framework for semi-structured table question answering that treats"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Extensive experiments across a diverse suite of structured and semi-structured table question answering benchmarks demonstrate that OmniTQA consistently outperforms existing symbolic, semantic, and hybrid baselines in both accuracy and cost efficiency. These gains are particularly pronounced for complex queries, large tables and multi-relation schemas.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that LLM inference latency and cost can be sufficiently controlled through atomic decomposition, operator reordering, and batching without introducing unacceptable accuracy trade-offs or requiring extensive per-workload tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"OmniTQA integrates LLM semantic reasoning as a first-class query operator with classical relational operators in a cost-aware planner for hybrid structured and semi-structured data.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"OmniTQA turns LLM semantic reasoning into an optimizable operator inside relational query plans to process mixed structured and textual tables more accurately and at lower cost than pure symbolic or pure semantic methods.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b61ce8e0763e09a461302641f4e41ed6071d35967a9b9d17c6b23b468f1767f4"},"source":{"id":"2604.02444","kind":"arxiv","version":2},"verdict":{"id":"8bfda4bb-68e7-42b0-999e-d77bab8c2837","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T20:13:08.575144Z","strongest_claim":"Extensive experiments across a diverse suite of structured and semi-structured table question answering benchmarks demonstrate that OmniTQA consistently outperforms existing symbolic, semantic, and hybrid baselines in both accuracy and cost efficiency. These gains are particularly pronounced for complex queries, large tables and multi-relation schemas.","one_line_summary":"OmniTQA integrates LLM semantic reasoning as a first-class query operator with classical relational operators in a cost-aware planner for hybrid structured and semi-structured data.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that LLM inference latency and cost can be sufficiently controlled through atomic decomposition, operator reordering, and batching without introducing unacceptable accuracy trade-offs or requiring extensive per-workload tuning.","pith_extraction_headline":"OmniTQA turns LLM semantic reasoning into an optimizable operator inside relational query plans to process mixed structured and textual tables more accurately and at lower cost than pure symbolic or pure semantic methods."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.02444/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}