TEN: Table Explicitization, Neurosymbolically

• URL: http://arxiv.org/abs/2508.09324v1
• Date: Tue, 12 Aug 2025 20:16:41 GMT
• Title: TEN: Table Explicitization, Neurosymbolically
• Abstract summary: We present a neurosymbolic approach, TEN, for extracting data from text input.<n>Our experiments demonstrate that TEN significantly outperforms purely neurals across multiple datasets and metrics.<n>A 21-participant user study confirms that TEN's tables are rated significantly more accurate.
• Score: 13.178005058859583
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present a neurosymbolic approach, TEN, for extracting tabular data from semistructured input text. This task is particularly challenging for text input that does not use special delimiters consistently to separate columns and rows. Purely neural approaches perform poorly due to hallucinations and their inability to enforce hard constraints. TEN uses Structural Decomposition prompting - a specialized chain-of-thought prompting approach - on a large language model (LLM) to generate an initial table, and thereafter uses a symbolic checker to evaluate not only the well-formedness of that table, but also detect cases of hallucinations or forgetting. The output of the symbolic checker is processed by a critique-LLM to generate guidance for fixing the table, which is presented to the original LLM in a self-debug loop. Our extensive experiments demonstrate that TEN significantly outperforms purely neural baselines across multiple datasets and metrics, achieving significantly higher exact match accuracy and substantially reduced hallucination rates. A 21-participant user study further confirms that TEN's tables are rated significantly more accurate (mean score: 5.0 vs 4.3; p = 0.021), and are consistently preferred for ease of verification and correction, with participants favoring our method in over 60% of the cases.

Related papers

• Solving In-Table Prediction Problems by Deep Neural Networks with Performance Evaluation Using Synthetic Data [4.657670532006343]
  In this work, we explore a different approach by employing deep NNs to learn relationships among individual columns within a given table.<n>We investigate whether NNs can predict the values of arbitrarily selected columns in a given table based on the remaining known columns.<n>A self-supervised learning approach is applied to address this problem by randomly selecting columns to be masked out and used as learning targets.
  arXiv  Detail & Related papers  (2026-09-01T13:53:12Z)
• Noise Immunity in In-Context Tabular Learning: An Empirical Robustness Analysis of TabPFN's Attention Mechanisms [0.0]
  Tabular foundation models (TFMs) generalize across heterogeneous datasets through in-context learning (ICL)<n>We study TabPFN and its attention mechanisms for binary classification problems with controlled synthetic perturbations.<n>We analyze internal signals including attention concentration and attention-based feature ranking metrics.
  arXiv  Detail & Related papers  (2026-04-06T17:16:37Z)
• GLEAN: Grounded Lightweight Evaluation Anchors for Contamination-Aware Tabular Reasoning [0.5414847001704249]
  We propose a lightweight evaluation protocol that integrates contamination-aware probes, weak-supervision governance, retrieval-reasoning diagnostics, and structured error attribution.<n>We evaluate across TabFact, WTQ via Squall, TableBench, RobuT, and SciTab under a 16GB GPU budget.
  arXiv  Detail & Related papers  (2026-01-22T13:56:19Z)
• An Empirical Investigation of Robustness in Large Language Models under Tabular Distortions [8.023379679609151]
  Large language models (LLMs) fail when tabular data in an otherwise canonical representation is subjected to semantic and structural distortions.<n>Only when provided with an explicit prior, via a system prompt, do models partially adjust their reasoning strategies and correct some distortions, though not consistently or completely.
  arXiv  Detail & Related papers  (2026-01-08T15:10:32Z)
• CMT-Bench: Cricket Multi-Table Generation Benchmark for Probing Robustness in Large Language Models [11.167804698594866]
  We present CMT-Bench, a diagnostic benchmark built from live cricket commentary.<n>We find large drops without extractive summaries, monotonic degradation with input length, and consistent accuracy drop under entity-form changes.
  arXiv  Detail & Related papers  (2025-10-20T23:51:28Z)
• Adverse Event Extraction from Discharge Summaries: A New Dataset, Annotation Scheme, and Initial Findings [1.9036581654832787]
  We present a manually annotated corpus for Adverse Event (AE) extraction from discharge summaries of elderly patients.<n>The dataset includes 14 clinically significant AEs-such as falls, delirium, and intracranial haemorrhage.<n>We evaluate multiple models using FlairNLP across three annotation granularities.
  arXiv  Detail & Related papers  (2025-06-17T18:13:40Z)
• TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuning [18.178908245791582]
  TableDreamer is a progressive and weakness-guided data synthesis framework for table instruction tuning.<n>It boosts the average accuracy of Llama3.1-8B-instruct by 11.62% (49.07% to 60.69%) with 27K GPT-4o synthetic data.<n>It outperforms state-of-the-art data synthesis baselines which use more training data.
  arXiv  Detail & Related papers  (2025-06-10T09:57:59Z)
• GliLem: Leveraging GliNER for Contextualized Lemmatization in Estonian [0.21485350418225246]
  We present GliLem, a novel hybrid lemmatization system for Estonian.<n>We leverage the flexibility of a pre-trained GliNER model to improve the lemmatization accuracy of Vabamorf.
  arXiv  Detail & Related papers  (2024-12-29T22:02:00Z)
• Interpretable Medical Diagnostics with Structured Data Extraction by Large Language Models [59.89454513692417]
  Tabular data is often hidden in text, particularly in medical diagnostic reports. We propose a novel, simple, and effective methodology for extracting structured tabular data from textual medical reports, called TEMED-LLM. We demonstrate that our approach significantly outperforms state-of-the-art text classification models in medical diagnostics.
  arXiv  Detail & Related papers  (2023-06-08T09:12:28Z)
• STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables [64.0903766169603]
  We propose a framework for few-shot semi-supervised learning, coined Self-generated Tasks from UNlabeled Tables (STUNT) Our key idea is to self-generate diverse few-shot tasks by treating randomly chosen columns as a target label. We then employ a meta-learning scheme to learn generalizable knowledge with the constructed tasks.
  arXiv  Detail & Related papers  (2023-03-02T02:37:54Z)
• SUN: Exploring Intrinsic Uncertainties in Text-to-SQL Parsers [61.48159785138462]
  This paper aims to improve the performance of text-to-dependence by exploring the intrinsic uncertainties in the neural network based approaches (called SUN) Extensive experiments on five benchmark datasets demonstrate that our method significantly outperforms competitors and achieves new state-of-the-art results.
  arXiv  Detail & Related papers  (2022-09-14T06:27:51Z)
• LNN-EL: A Neuro-Symbolic Approach to Short-text Entity Linking [62.634516517844496]
  We propose LNN-EL, a neuro-symbolic approach that combines the advantages of using interpretable rules with the performance of neural learning. Even though constrained to using rules, LNN-EL performs competitively against SotA black-box neural approaches.
  arXiv  Detail & Related papers  (2021-06-17T20:22:45Z)
• Detecting Hallucinated Content in Conditional Neural Sequence Generation [165.68948078624499]
  We propose a task to predict whether each token in the output sequence is hallucinated (not contained in the input) We also introduce a method for learning to detect hallucinations using pretrained language models fine tuned on synthetic data.
  arXiv  Detail & Related papers  (2020-11-05T00:18:53Z)
• DeepEnroll: Patient-Trial Matching with Deep Embedding and Entailment Prediction [67.91606509226132]
  Clinical trials are essential for drug development but often suffer from expensive, inaccurate and insufficient patient recruitment. DeepEnroll is a cross-modal inference learning model to jointly encode enrollment criteria (tabular data) into a shared latent space for matching inference.
  arXiv  Detail & Related papers  (2020-01-22T17:51:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.