TELLER: Dual-Path Iterative Preference Optimization for Table Entity Linking

• URL: http://arxiv.org/abs/2607.28680v1
• Date: Wed, 29 Jul 2026 18:08:26 GMT
• Title: TELLER: Dual-Path Iterative Preference Optimization for Table Entity Linking
• Abstract summary: We present TELLER: Table Entity Linking through Learning from Errors and Reasoning.<n>We first retrieve and rank Wikidata candidates and retain reduced table evidence in the prompt.<n>The direct-answer path applies iterative direct preference optimization and refreshes its preference data with residual errors from the updated model.
• Score: 1.1542896774745293
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Entity linking in tables matches short and ambiguous cell mentions to their corresponding knowledge-base entities. Existing approaches typically rely on data preprocessing pipelines that retain either compact or extensive table content as contextual evidence, and then formulate entity linking as a language generation task for instruction-tuned models; recent systems further incorporate explicit reasoning to disambiguate challenging mentions. However, their training supervision is usually static: fixed preference data cannot adapt to the residual errors of an evolving model, while variations in reasoning length can bias sequence-level preference learning. To address these limitations, we present TELLER: Table Entity Linking through Learning from Errors and Reasoning. We first retrieve and rank Wikidata candidates and retain reduced table evidence in the prompt. The direct-answer path applies iterative direct preference optimization and refreshes its preference data with residual errors from the updated model. The reasoning path uses filtered and compressed chain-of-thought rationales for supervised fine-tuning, followed by our iterative length-normalized regularized preference optimization. On the TableInstruct entity-linking subset, the direct-answer path improves accuracy from 94.35\% to 94.50\%; on the MammoTab V2 evaluation set, it improves accuracy from 87.59\% to 88.20\%. The reasoning path improves accuracy from 92.90\% to 92.95\% on TableInstruct and from 79.09\% to 81.85\% on MammoTab V2, while maintaining high rates of complete reasoning generation. These results show that iterative preference learning benefits both concise entity prediction and explicit reasoning.

Related papers

• REER-PT: Reverse-Engineered Reasoning for Perplexity-Guided Pre-training Data Augmentation [64.84437332310516]
  We introduce textbfREER-PT, a scalable framework that extends Reverse-Engineered Reasoning (REER) to raw pre-training data.<n>REER-PT identifies continuations that are difficult to predict but can still be inferred from the preceding context, and inserts concise reasoning annotations that reconstruct the missing connection between context and continuation.<n>This sparse transformation preserves the source text and remains compatible with standard next-token prediction, avoiding online reasoning rollouts during pre-training.
  arXiv  Detail & Related papers  (2026-08-31T11:34:19Z)
• When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors [36.695407633693286]
  We present the first systematic evaluation of data referencing errors (DREs) across different models and tasks.<n>Our results show that DREs occur across all tested models (1.7B to 20B parameters)<n>We demonstrate that incorporating data referencing as a critic significantly improves answer accuracy up to 12.0%.
  arXiv  Detail & Related papers  (2026-06-30T17:54:50Z)
• Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimization [54.749573452394664]
  We find that accuracy collapses as instance data grows, even when the formulation itself is simple.<n>We address this via a simple inference-time approach, BIND, which externalizes numeric data to structured files so the model binds data rather than from prompt prompt.<n>We validate our hypothesis by finetuning a model exclusively on binding and show that it outperforms end-to-end SFT and RL across three structurally distinct optimization categories.
  arXiv  Detail & Related papers  (2026-05-20T21:25:41Z)
• LIFT: Last-Mile Fine-Tuning for Table Explicitation [3.0657548822958063]
  We propose Lift, a pipeline in which a pre-trained large language model extracts an initial table from unstructured clipboard text.<n>On a benchmark of 2,596 tables from three datasets, Lift matches or exceeds end-to-end SLM fine-tuning.
  arXiv  Detail & Related papers  (2026-05-13T12:19:01Z)
• TopBench: A Benchmark for Implicit Prediction and Reasoning over Tabular Question Answering [80.93487993878836]
  A common class of real-world queries is implicitly predictive, requiring the inference of unobserved answers from historical patterns rather than mere retrieval.<n>These queries introduce two challenges: recognizing latent intent and reliable predictive reasoning over massive tables.<n>We introduce TopBench, a benchmark consisting of 779 samples across four sub-tasks, ranging from single-point prediction to decision making, treatment effect analysis, and complex reasoning.
  arXiv  Detail & Related papers  (2026-04-30T16:22:51Z)
• QUIETT: Query-Independent Table Transformation for Robust Reasoning [21.03903792753972]
  Real-world tables often exhibit irregular schemas, heterogeneous value formats, and implicit relational structure.<n>We introduce QuIeTT, a query-independent table transformation framework.<n>We show consistent gains across models and reasoning paradigms, with particularly strong improvements on a challenge set of structurally diverse, unseen questions.
  arXiv  Detail & Related papers  (2026-02-23T16:23:49Z)
• TabSieve: Explicit In-Table Evidence Selection for Tabular Prediction [14.270578219134997]
  We propose TabSieve, a select-then-predict framework that makes evidence usage explicit and auditable.<n>Given a table and a query row, TabSieve first selects a small set of informative rows as evidence and then predicts the missing target conditioned on the selected evidence.<n>Experiments on a held-out benchmark of 75 classification and 52 regression tables show that TabSieve consistently improves performance across shot budgets.
  arXiv  Detail & Related papers  (2026-02-12T08:28:58Z)
• Reasoning by Commented Code for Table Question Answering [2.497926557563177]
  Table Question Answering (TableQA) poses a significant challenge for large language models.<n>Existing methods, which depend on end-to-end answer generation or single-line program queries, exhibit limited numerical accuracy and reduced interpretability.<n>This work introduces a commented, step-by-step code-generation framework that incorporates explicit reasoning into the Python program-generation process.
  arXiv  Detail & Related papers  (2026-01-31T06:16:35Z)
• CORE-T: COherent REtrieval of Tables for Text-to-SQL [91.76918495375384]
  CORE-T is a scalable, training-free framework that enriches tables with purpose metadata and pre-computes a lightweight table-compatibility cache.<n>Across Bird, Spider, and MMQA, CORE-T improves table-selection F1 by up to 22.7 points while retrieving up to 42% fewer tables.
  arXiv  Detail & Related papers  (2026-01-19T14:51:23Z)
• Knowing the Answer Isn't Enough: Fixing Reasoning Path Failures in LVLMs [85.37131922131657]
  We reveal a critical yet underexplored flaw in Large Vision-Language Models (LVLMs)<n>Even when these models know the correct answer, they frequently arrive there through incorrect reasoning paths.<n>We propose PSO (Path-Select Optimization), a two-stage post-training framework designed to enhance both the reasoning performance and stability of existing LVLMs.
  arXiv  Detail & Related papers  (2025-12-06T03:02:55Z)
• KET-QA: A Dataset for Knowledge Enhanced Table Question Answering [63.56707527868466]
  We propose to use a knowledge base (KB) as the external knowledge source for TableQA. Every question requires the integration of information from both the table and the sub-graph to be answered. We design a retriever-reasoner structured pipeline model to extract pertinent information from the vast knowledge sub-graph.
  arXiv  Detail & Related papers  (2024-05-13T18:26:32Z)
• OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering [106.73213656603453]
  We develop a simple table-based QA model with minimal annotation effort. We propose an omnivorous pretraining approach that consumes both natural and synthetic data.
  arXiv  Detail & Related papers  (2022-07-08T01:23:45Z)

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.