Decompose--Enhance--Correct (Decompose--Enhance--Correct), a visual-consistency-guided agentic framework that improves frozen table parsers without retraining is proposed, which derives a 1,977-table Consensus-Hard Set from 4,556 candidates through offline metrics and cross-model consensus.
Abstract
Recent document parsers achieve table TEDS scores above 93 on OmniDocBench v1.6, yet community feedback and our audit reveal persistent failures on complex real-world tables. To quantify this gap, we introduce TableParseMap, a diagnostic benchmark of 916 real-world tables organized into five challenging scenarios and nine failure types. The strongest evaluated parser achieves only 85.03 TEDS, showing that aggregate benchmark scores conceal substantial weaknesses. Our analysis attributes these failures to three complementary limitations: large tables exceed the reliable processing scale of a single pass, weak or ambiguous visual cues hinder structure perception, and the reconstructed table may remain visually inconsistent with the image. We therefore propose DEC (Decompose--Enhance--Correct), a visual-consistency-guided agentic framework that improves frozen table parsers without retraining. DEC uses a general VLM as the controller: Decompose partitions large tables along structure-aware boundaries, Enhance exposes weak visual evidence and reparses transformed views, and Correct diagnoses and repairs residual errors. A Visual Consistency Gate (VC-Gate) selectively triggers intervention, while a Visual Consistency Ranker (VC-Ranker) verifies candidate updates and supports rollback without ground-truth HTML at inference time. We further derive a 1,977-table Consensus-Hard Set from 4,556 candidates through offline metrics and cross-model consensus. Across three frozen parsers, DEC improves TEDS by 1.57 points on average; on TableParseMap, gains reach 1.89 points overall, 2.62 on structural errors, and 5.66 on large tables.
These findings establish learned sparse retrieval as a highly impactful design choice in automated fact-checking, with retrieval quality serving as a critical determinant of end-to-end performance in the studied systems.
Ritvik Setty, Vinay Setty· International Conference on...· 0 citations
SABRE is established as a reusable framework for constructing and refreshing VLM stress tests rather than a single fixed benchmark, and the results establish SABRE as a reusable framework for constructing and refreshing VLM stress tests rather than a single fixed benchmark.
Zixuan Lan, Luzhe Sun, Matthew R. Walter et al.· 0 citations
The majority of data in businesses and industries is stored in tables, databases, and data warehouses. Reasoning with table-structured data poses significant challenges for large language models (LLMs) due to its hidden semantics, inherent complexity, and structured nature. One of these challenges is lacking an effective evaluation benchmark fairly reflecting the performances of LLMs on broad table reasoning abilities. In this paper, we fill in this gap by presenting a comprehensive table reasoning benchmark, TReB. Firstly, we propose a taxonomy to systematically measure both shallow table understanding abilities and deep table reasoning abilities, covering a total of 26 sub-tasks. We then construct a high quality dataset through a dedicated data processing and synthesis procedure. Based on these well-constructed samples, we design an evaluation framework to robustly measure table reasoning capabilities with three distinct inference modes. Experimental results with our data and framework reveal that existing LLMs still have significant room for improvement in addressing the complex and real world table related tasks. Both the dataset and evaluation framework are publicly available, with the dataset hosted on huggingface.co/datasets/JT-LM/JIUTIAN-TReB, and the framework on github.com/JT-LM/jiutian-treb.
Ce Li, Xiaofan Liu, Zhiyan Song et al.· Annual International ACM SIG...· 3 citations
This work introduces a metamorphic testing framework that evaluates the consistency of RAG systems under corpus evolution, formalising a fault taxonomy and 11 mutation operators that systematically perturb the system at both the pre-chunk (retrieval index) and post-chunk (retrieved context) levels.
Jinhan Kim, Samuele Pasini, Paolo Tonella· 1 citation
Accuracy changes after language-model self-revision are usually interpreted as changes in reasoning. We show this can fail at the answer-extraction boundary, and test the failure causally rather than only observationally. Across Qwen3.5 (0.8B-9B), Gemma-4-12B, and two frontier models via API (Tencent Hy3, Nvidia Nemotron-3-Ultra-550B) in 29 primary cells plus a frontier arm, we decompose the always-revise accuracy shift into a content margin (both answers parseable) and format-recovery/loss margins (parseability changes). On 12 cells with meaningful unparseable-answer rates, format effects exceed content effects (Wilcoxon p=1.7e-3). To test this causally, we force already-generated reasoning through grammar-constrained decoding so every answer is parseable by construction: across 14 cells this closes a median 71% of the gap between the naive total effect and the content-margin estimate, with two cells converging exactly and a residual on the two largest-effect cells reported rather than dismissed. A clustered model confirms floor-scale (0.8B/2B) models have far higher odds of content-level change and harm than capable-scale models (p<1e-7). Replicating a cited confidence-gating protocol verbatim on Qwen3.5 does not reproduce its reported gain and shows the same near-zero content margin. A frontier check on much larger models shows format-dominance intensifying with scale: content margin is exactly zero in all 5 cells despite total effects up to +0.275, though this arm is lower-powered. The calibration-floor criterion on the content margin reveals a squeeze: floor-scale cells have headroom but insufficient signal, capable-scale cells have signal but little headroom; only one cell is marginally viable, with negligible sealed-holdout gain. Content is a minority share of what the field has measured as self-correction. We release the instrument, code, and derived results.