Papers › Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for...

Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning

31 Jan 2023arXiv:2301.13808archive 2025-07-28

Yunhu Ye, Binyuan Hui, Min Yang, Binhua Li, Fei Huang, Yongbin Li

Table-based reasoning has shown remarkable progress in combining deep models with discrete reasoning, which requires reasoning over both free-form natural language (NL) questions and structured tabular data. However, previous table-based reasoning solutions usually suffer from significant performance degradation on huge evidence (tables). In addition, most existing methods struggle to reason over complex questions since the required information is scattered in different places. To alleviate the above challenges, we exploit large language models (LLMs) as decomposers for effective table-based reasoning, which (i) decompose huge evidence (a huge table) into sub-evidence (a small table) to mitigate the interference of useless information for table reasoning; and (ii) decompose complex questions into simpler sub-questions for text reasoning. Specifically, we first use the LLMs to break down the evidence (tables) involved in the current question, retaining the relevant evidence and excluding the remaining irrelevant evidence from the huge table. In addition, we propose a "parsing-execution-filling" strategy to alleviate the hallucination dilemma of the chain of thought by decoupling logic and numerical computation in each step. Extensive experiments show that our method can effectively leverage decomposed evidence and questions and outperforms the strong baselines on TabFact, WikiTableQuestion, and FetaQA datasets. Notably, our model outperforms human performance for the first time on the TabFact dataset.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

alibabaresearch/damo-convai officialmentioned in paperpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Dial2vec: Self-Guided Contrastive Learning of Unsupervised Dialogue Embeddings (arXiv:2210.15332; that paper's own run record: 7 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified), PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts (arXiv:2305.14839; that paper's own run record: 0 ran · 1 unverified) and SDPO: Segment-Level Direct Preference Optimization for Social Agents (arXiv:2501.01821; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
google-research/chain-of-table mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding (arXiv:2401.04398; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

HallucinationSemantic ParsingTable-based Fact Verification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Parsing WikiTableQuestions Dater Accuracy (Dev) 64.8 #10 of 22 Archive leaderboard report
Semantic Parsing WikiTableQuestions Dater Accuracy (Test) 65.9 #10 of 22 Archive leaderboard report
Table-based Fact Verification TabFact Dater Test 93.0 #2 of 15 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections