TALENT: Table VQA via Augmented Language-Enhanced Natural-text Transcription

• URL: http://arxiv.org/abs/2510.07098v1
• Date: Wed, 08 Oct 2025 14:56:42 GMT
• Title: TALENT: Table VQA via Augmented Language-Enhanced Natural-text Transcription
• Authors: Guo Yutong, Wanying Wang, Yue Wu, Zichen Miao, Haoyu Wang,
• Abstract summary: Table Visual Question Answering (Table VQA) is typically addressed by large vision-language models (VLMs)<n>We propose TALENT, a lightweight framework that leverages dual representations of tables.
• Score: 15.734561144090641
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Table Visual Question Answering (Table VQA) is typically addressed by large vision-language models (VLMs). While such models can answer directly from images, they often miss fine-grained details unless scaled to very large sizes, which are computationally prohibitive, especially for mobile deployment. A lighter alternative is to have a small VLM perform OCR and then use a large language model (LLM) to reason over structured outputs such as Markdown tables. However, these representations are not naturally optimized for LLMs and still introduce substantial errors. We propose TALENT (Table VQA via Augmented Language-Enhanced Natural-text Transcription), a lightweight framework that leverages dual representations of tables. TALENT prompts a small VLM to produce both OCR text and natural language narration, then combines them with the question for reasoning by an LLM. This reframes Table VQA as an LLM-centric multimodal reasoning task, where the VLM serves as a perception-narration module rather than a monolithic solver. Additionally, we construct ReTabVQA, a more challenging Table VQA dataset requiring multi-step quantitative reasoning over table images. Experiments show that TALENT enables a small VLM-LLM combination to match or surpass a single large VLM at significantly lower computational cost on both public datasets and ReTabVQA.

Related papers

• MATA: Multi-Agent Framework for Reliable and Flexible Table Question Answering [6.7895562627088735]
  We introduce MATA, a multi-agent TableQA framework that leverages multiple complementary reasoning paths and a set of tools built with small language models.<n>MATA generates candidate answers through diverse reasoning styles for a given table and question, then refines or selects the optimal answer.<n>It incorporates an algorithm designed to minimize expensive Large Language Models agent calls, enhancing overall efficiency.
  arXiv  Detail & Related papers  (2026-02-10T10:43:02Z)
• 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)
• TableDART: Dynamic Adaptive Multi-Modal Routing for Table Understanding [52.59372043981724]
  TableDART is a training-efficient framework that integrates multimodal views by reusing pretrained single-modality models.<n>In addition, we propose a novel agent to cross-modal knowledge integration by analyzing outputs from text- and image-based models.
  arXiv  Detail & Related papers  (2025-09-18T07:00:13Z)
• Are Prompts All You Need? Evaluating Prompt-Based Large Language Models (LLM)s for Software Requirements Classification [1.1458853556386799]
  This study tests whether prompt based large language models can reduce data needs.<n>We benchmark several models and prompting styles across multiple tasks on two English datasets, PROMISE and SecReq.
  arXiv  Detail & Related papers  (2025-09-17T09:58:26Z)
• Distill Visual Chart Reasoning Ability from LLMs to MLLMs [64.32993770646165]
  Solving complex chart Q&A tasks requires advanced visual reasoning abilities in multimodal large language models (MLLMs)<n>We propose Code-as-Intermediary Translation (CIT), a cost-effective, efficient and scalable data synthesis method for distilling visual reasoning abilities from LLMs to MLLMs.<n>ReachQA is a dataset containing 3k reasoning-intensive charts and 20k Q&A pairs to enhance both recognition and reasoning abilities of MLLMs.
  arXiv  Detail & Related papers  (2024-10-24T14:50:42Z)
• TableRAG: Million-Token Table Understanding with Language Models [53.039560091592215]
  TableRAG is a Retrieval-Augmented Generation (RAG) framework specifically designed for LM-based table understanding.<n>TableRAG leverages query expansion combined with schema and cell retrieval to pinpoint crucial information before providing it to the LMs.<n>Our results demonstrate that TableRAG achieves the highest retrieval quality, leading to the new state-of-the-art performance on large-scale table understanding.
  arXiv  Detail & Related papers  (2024-10-07T04:15:02Z)
• Table Question Answering for Low-resourced Indic Languages [71.57359949962678]
  TableQA is the task of answering questions over tables of structured information, returning individual cells or tables as output. We introduce a fully automatic large-scale tableQA data generation process for low-resource languages with limited budget. We incorporate our data generation method on two Indic languages, Bengali and Hindi, which have no tableQA datasets or models.
  arXiv  Detail & Related papers  (2024-10-04T16:26:12Z)
• HiddenTables & PyQTax: A Cooperative Game and Dataset For TableQA to Ensure Scale and Data Privacy Across a Myriad of Taxonomies [9.09415727445941]
  We propose a cooperative game dubbed "HiddenTables" as a potential resolution to this challenge. "HiddenTables" is played between the code-generating "r" and the "Oracle windows" which evaluates the ability of the agents to solve Table QA tasks. We provide evidential experiments on a diverse set of tables that demonstrate an LLM's collective inability to generalize and perform on complex queries.
  arXiv  Detail & Related papers  (2024-06-16T04:53:29Z)
• Multimodal Table Understanding [26.652797853893233]
  How to directly understand tables using intuitive visual information is a crucial and urgent challenge for developing more practical applications. We propose a new problem, multimodal table understanding, where the model needs to generate correct responses to various table-related requests. We develop Table-LLaVA, a generalist multimodal large language model (MLLM), which significantly outperforms recent open-source MLLM baselines on 23 benchmarks.
  arXiv  Detail & Related papers  (2024-06-12T11:27:03Z)
• TableVQA-Bench: A Visual Question Answering Benchmark on Multiple Table Domains [4.828743805126944]
  This paper establishes a benchmark for table visual question answering, referred to as the TableVQA-Bench. It is important to note that existing datasets have not incorporated images or QA pairs, which are two crucial components of TableVQA.
  arXiv  Detail & Related papers  (2024-04-30T02:05:18Z)
• TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning [55.33939289989238]
  We propose TAP4LLM as a versatile pre-processor suite for leveraging large language models (LLMs) in table-based tasks effectively. It covers several distinct components: (1) table sampling to decompose large tables into manageable sub-tables based on query semantics, (2) table augmentation to enhance tables with additional knowledge from external sources or models, and (3) table packing & serialization to convert tables into various formats suitable for LLMs' understanding.
  arXiv  Detail & Related papers  (2023-12-14T15:37:04Z)
• Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study [44.39031420687302]
  Large language models (LLMs) are becoming attractive as few-shot reasoners to solve Natural Language (NL)-related tasks. We try to understand this by designing a benchmark to evaluate the structural understanding capabilities of LLMs. We propose $textitself-augmentation$ for effective structural prompting, such as critical value / range identification.
  arXiv  Detail & Related papers  (2023-05-22T14:23:46Z)
• Large Language Models are few(1)-shot Table Reasoners [31.036914270008978]
  Large language models (LLMs) are generally excellent few-shot reasoners to solve text reasoning tasks. In this paper, we aim at understanding how well LLMs can perform on table tasks with few-shot in-context learning.
  arXiv  Detail & Related papers  (2022-10-13T04:08:24Z)

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.