PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understanding

Md Mahadi Hasan Nahid; Davood Rafiei

cs.CLAug 25, 2026

PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understanding

Authors: Md Mahadi Hasan Nahid, Davood Rafiei

Organizations: University of Alberta

Abstract

Large Language Models (LLMs) have shown strong capabilities in table reasoning, but their effectiveness degrades as tables grow in size and complexity due to irrelevant context and difficulty localizing the evidence required for reasoning. Existing approaches typically reason over either the full table or a single reduced view, which can still obscure important row-column relationships. We introducePARTAB (Partition-Aware Reasoning overTables), a framework that constructs a structured evidence interface between the LLM and the table. PARTAB represents query-relevant evidence as semantically coherent, row-linked table regions and performs hierarchical selection over column groups and row-level partitions before composing the selected evidence for answer generation. We evaluate PARTAB on multiple table reasoning benchmarks, covering question answering, fact verification, and numerical reasoning. PARTAB consistently improves over full-table prompting and several recent table reasoning methods, achieving strong performance on WikiTableQuestions and TabFact while remaining competitive on numerical reasoning. Additional analyses show that semantic partitioning and targeted evidence selection improve evidence localization, substantially reduce the reasoning context, and provide larger benefits on complex tables. These results demonstrate the value of structured, partition aware evidence construction for scalable table reasoning.

Figures & tables

Figure 1: Comparison of reasoning behaviors under different table reasoning paradigms. (I) Full-table prompting exposes the model to the entire table, increasing irrelevant context and making evidence localization more difficult in long and wide tables. (II) Single-view pruning reduces context size but may remove required evidence, leading to incomplete reasoning and incorrect aggregation. All data shown are synthetic and for illustration only.

Figure 2: Overview of PARTAB. Given a question and table, PARTAB constructs semantically coherent table partitions and performs localized understanding over selected partitions enabling reliable reasoning over large and noisy tables. All data shown are synthetic and for illustration only .

Method	WikiTableQuestions	TabFact	TableBench
Method	EM	Acc	NR (EM)	FC (EM)
BINDER ( Cheng et al., 2023 )	38.03	67.50	-	-
DATER ( Ye et al., 2023 )	52.00	74.70	-	-
ReAcTable ( Zhang et al., 2024b )	57.09	-	-	-
End-to-End Prompting	59.43	73.22	59.50	66.66
Chain-of-Thought (CoT)	64.31	75.99	-	-

Table 1: Downstream performance on table reasoning benchmarks. PARTAB achieves strong results across question answering, fact verification, and numerical reasoning, outperforming several recent baselines on WikiTableQuestions and TabFact while remaining competitive on TableBench.

Figure 3: Partition construction performance. Manual evaluation of semantic column-grouping quality over 100 tables.The generated groups are fully coherent in 96% of the evaluated cases.

Selection Strategy	WikiTQ	TabFact	TableBench
	EM	Acc	NR (EM)	FC (EM)
Basic Selection	74.71	87.88	64.43	79.26
Similarity-based Selection	67.25	85.87	58.69	59.25
LLM-based Selection	79.31	90.48	70.33	82.71

Table 2: Comparison of part-selection strategies across table reasoning benchmarks. The best result in each column is shown in bold.

Figure 4: Distribution of the number of semantic column groups generated per table. Most tables are decomposed into three or four groups across all evaluated datasets.

LLM Backbone	WikiTQ	TabFact	TableBench
	EM	Acc	NR (EM)	FC (EM)
GPT-4o-mini	79.31	90.48	70.33	82.71
Gemini-2.5-Flash-Lite	71.23	83.56	61.29	64.53
DeepSeek-v4-Flash	78.30	91.70	70.23	75.34

Table 3: Performance of PARTAB across different answer-execution backbones.

LLM Backbone	Method	WikiTQ-Hard		TabFact-Hard		TB-NR-Hard
LLM Backbone	Method	EM	${\Delta}$	EM	${\Delta}$	EM	${\Delta}$
GPT-4o-mini	Full Table	45.80	–	55.32	–	40.47	–
GPT-4o-mini	PARTAB (Ours)	55.72	+9.92	80.85	+25.53	61.90	+21.43
GPT-5-mini	Full Table	60.30	–	57.14	–	57.45	–
GPT-5-mini	PARTAB (Ours)	61.83	+1.53	78.26	+21.12	61.90	+4.45
DeepSeek-v4-Pro	Full Table	58.01	–	55.32	–	54.76	–

Table 4: Performance of full-table prompting and PARTAB on hard subsets containing large or wide tables. WikiTQ-Hard and TB-NR-Hard are evaluated using Exact Match (EM), while TabFact-Hard is evaluated using accuracy. Each

\Delta

denotes the absolute improvement of PARTAB over full-table prompting with the same backbone.

Dataset	Partition Construction			Partition Selection
Dataset	Groups / Table	Columns / Group	Parts / Table	Selected Parts	Reduction (%)
WikiTQ	3.13	2.10	17.56	3.88	77.9
TabFact	3.17	2.11	9.84	2.44	75.2
TableBench	3.32	2.31	12.27	3.04	75.2

Table 5: Statistics of partition construction and selection. Reduction is computed as

1-\frac{\text{selected parts}}{\text{candidate parts}}

Configuration	WikiTQ
Configuration	EM	${\Delta}$
Full PARTAB	79.31	–
PARTAB w/o Question Analyzer	72.21	$-7.10$
PARTAB with Random Column Grouping	68.84	$-10.47$
PARTAB with Row Chunking Only	57.19	$-22.12$

Table 6: Component-level ablation results on WikiTQ. Each

\Delta

denotes the absolute change in exact match relative to the full PARTAB configuration.

Figure 5: Distribution of failure types based on 100 incorrect predictions. Part-selection errors constitute the largest source of failure.

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Method	LLM Calls	WikiTQ EM
Full-table (Budget-matched)	5	64.61
PARTAB	5	79.31

Appendix

Table 7: Budget-matched comparison between repeated full-table prompting and PARTAB .

Dataset	Fallback Rate (%)	Evidence Recall (%)
WikiTQ	2.70	87.0 †
TabFact	1.90	–
TableBench	0.24	–

Appendix

Table 8: Selection stability across the evaluation datasets. † Evidence recall is based on manual annotation of 100 WikiTQ examples.

Method	LLM Calls	Avg. Tokens / Query	TabFact Acc.
Full-table prompting	1	2.1k	73.22
Chain-of-Table	$\leq 25$	13.2k	85.09
TableMaster	11	3.3k	90.12
PARTAB – Basic	4	2.1k	87.88
PARTAB – Similarity	4	1.6k	85.87
PARTAB – LLM-based	5	2.3k	90.48

Appendix

Table 9: Accuracy–efficiency comparison on TabFact. Token counts cover the complete per-query pipeline. Bold values indicate the lowest token usage and the highest accuracy, respectively.

Method	Avg. Selected Parts ↓	WikiTQ (EM)
Full Table	17.56	59.43
Basic Selection	6.50	74.71
Similarity-based	5.36	67.25
LLM-based	3.88	79.31

Appendix

Table 10: Partition reduction efficiency on WikiTableQuestions. We report the average number of selected parts and Exact Match (EM) accuracy.

Dataset	Number of Rows			Number of Columns
Dataset	Min	Avg	Max	Min	Avg	Max
WikiTableQuestions	5	25.65	517	3	6.39	21
TabFact	5	13.41	47	5	6.29	20
TableBench	6	16.75	176	4	6.64	20

Appendix

Table 11: Structural statistics of the evaluation datasets.

Panel of Figure 6 — Figure 6: Illustrative example of PARTAB on a multi-step numerical reasoning task. The table is truncated for clarity; ellipses ( $\dots$ ) indicate omitted columns and rows. PARTAB isolates the relevant metric columns, selects a small subset of partitions, and correctly computes the difference between the highest and lowest elevations.

Panel of Figure 7 — Figure 7: Illustrative example of PARTAB on a comparison-based reasoning task. The table is truncated for clarity; ellipses ( $\dots$ ) indicate omitted columns and rows. PARTAB selects the relevant semantic groups and partitions, enabling accurate identification of the most biodiverse country.

Panel of Figure 8 — Figure 8: Illustrative example of PARTAB on a lookup-based reasoning task. The table is truncated for clarity; ellipses ( $\dots$ ) indicate omitted rows and columns. PARTAB identifies the relevant row and extracts the country information from the athlete name field.

Panel of Figure 9 — Figure 9: Question Analyzer Prompt Template used to infer reasoning requirements from a natural language question.

Panel of Figure 10 — Figure 10: Column Grouping Prompt Template used to construct semantically coherent column groups for partition-aware table reasoning.

Panel of Figure 11 — Figure 11: Group Selection Prompt Template used to identify the minimum required semantic groups for answering a question.

Panel of Figure 12 — Figure 12: LLM-based Part Selection Prompt Template used to select the minimum required table parts from the candidate partition set.

Panel of Figure 13 — Figure 13: Answer Execution Prompt Template used to generate the final answer from the selected table parts.

Table Reasoning

See all 9 papers

From Table to Cell: Attention for Better Reasoning with TABALIGN
May 14, 2026Tung Sum Thomas Kwok, Zeyong Zhang, Xinyu Wang +6Table QA Table Reasoning
University of California, Los Angeles · SimpleWay · New Jersey Institute of Technology +4
TabScope: Question-Adaptive Scope Selection for Table Question Answering
Sep 3, 2026Yuxiang Wang, Junhao Gan, Jianzhong QiTable QA
The University of Melbourne
CRAFT: A Unified Counterfactual Reasoning Framework for Tabular Question Answering and Fact Verification
Jun 5, 2026Chenshuo Pan, Yu Zhao, Jie Zhang +7Table QA Claim Verification
Xingchen AGI Lab,China Telecom Artificial Intelligence Technology (Beijing) Co., Ltd

May 14, 2026J/K move · Enter open · S save

From Table to Cell: Attention for Better Reasoning with TABALIGN

Tung Sum Thomas Kwok, Zeyong Zhang, Xinyu Wang, Chunhe Wang+5

University of California, Los Angeles · SimpleWay · New Jersey Institute of Technology+4

Table QA Table Reasoning Structured Reasoning Diffusion Language Models LLM Reasoning

Open paper AskPDF arXiv

Multi-step LLM reasoning over structured tables fails because planning and execution share no explicit cell-grounding contract. Existing methods constrain the planner to a left-to-right factorization at odds with table permutation invariance, and score intermediate states by generated content alone, overlooking cell grounding. We conduct a pilot study showing that diffusion language models (DLMs) produce more human-aligned and permutation-stable cell attention on tables than autoregressive models, with a 40.2% median reduction in attention-AUROC variability under row reordering. Motivated by this, we propose TABALIGN, a planned table reasoning framework that operationalizes the contract. TABALIGN pairs a masked DLM planner, whose bidirectional denoising emits plan steps as binary cell masks, with TABATTN, a lightweight verifier trained on 1,600 human-verified attention standards to score each step by its attention overlap with the plan-designated mask. Across eight benchmarks covering table question answering and fact verification, TABALIGN improves average accuracy by 15.76 percentage points over the strongest open-source baseline at comparable 8B-class scale, with a matched-backbone ablation attributing 2.87 percentage points of this gain to the DLM planner over an AR planner on a fixed reasoner. Cleaner DLM plans also accelerate downstream reasoning execution by 44.64%.

Abstract

Table Reasoning

Explore similar work

From Table to Cell: Attention for Better Reasoning with TABALIGN

TabScope: Question-Adaptive Scope Selection for Table Question Answering

CRAFT: A Unified Counterfactual Reasoning Framework for Tabular Question Answering and Fact Verification