REVIEW 22 cited by
TableGPT2: A Large Multimodal Model with Tabular Data Integration
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
The emergence of models like GPTs, Claude, LLaMA, and Qwen has reshaped AI applications, presenting vast new opportunities across industries. Yet, the integration of tabular data remains notably underdeveloped, despite its foundational role in numerous real-world domains. This gap is critical for three main reasons. First, database or data warehouse data integration is essential for advanced applications; second, the vast and largely untapped resource of tabular data offers immense potential for analysis; and third, the business intelligence domain specifically demands adaptable, precise solutions that many current LLMs may struggle to provide. In response, we introduce TableGPT2, a model rigorously pre-trained and fine-tuned with over 593.8K tables and 2.36M high-quality query-table-output tuples, a scale of table-related data unprecedented in prior research. This extensive training enables TableGPT2 to excel in table-centric tasks while maintaining strong general language and coding abilities. One of TableGPT2's key innovations is its novel table encoder, specifically designed to capture schema-level and cell-level information. This encoder strengthens the model's ability to handle ambiguous queries, missing column names, and irregular tables commonly encountered in real-world applications. Similar to visual language models, this pioneering approach integrates with the decoder to form a robust large multimodal model. We believe the results are compelling: over 23 benchmarking metrics, TableGPT2 achieves an average performance improvement of 35.20% in the 7B model and 49.32% in the 72B model over prior benchmark-neutral LLMs, with robust general-purpose capabilities intact.
Forward citations
Cited by 22 Pith papers
-
SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner
SWE-Flow synthesizes incremental, test-driven development tasks from real GitHub projects and shows that fine-tuning Qwen2.5-Coder-32B-Instruct on them improves performance on the resulting SWE-Flow-Bench benchmark.
-
Data Analysis in the Wild: Benchmarking Large Language Models Against Real-World Data Complexities
DataGovBench is a new benchmark using 178 large multi-tabular government datasets showing state-of-the-art LLMs and agents achieve below 40% QA accuracy and below 50% insight scores, far from real-world data analysis demands.
-
IFEvalCode: Controlled Code Generation
A 1,620-sample, 8-language, Chinese/English benchmark separates code correctness from instruction-following and shows instruction compliance is far lower than correctness across 40+ LLMs.
-
SKA-Bench: A Fine-Grained Benchmark for Evaluating Structured Knowledge Understanding of LLMs
SKA-Bench is a fine-grained QA benchmark across KG, table, and hybrid formats that shows current LLMs remain sensitive to noise and order and often hallucinate instead of rejecting unanswerable inputs.
-
LLM4Hint: Leveraging Large Language Models for Hint Recommendation in Offline Query Optimization
A hybrid LLM-and-encoder framework recommends query optimization hints offline and reports better speedup and latency than Bao, Lero, and FASTgres.
-
Table-r1: Self-supervised and Reinforcement Learning for Program-based Table Reasoning in Small Language Models
Table-r1 combines a layout-transformation self-supervised task and a mix-paradigm GRPO stage so 7B/8B models outperform other small-model table reasoners and approach GPT-4o-level accuracy.
-
Griffin: Towards a Graph-Centric Relational Database Foundation Model
A single pretrained graph model for relational databases, Griffin unifies encoders and decoders and reports the best average rank across 24 tasks in its evaluation.
-
CoddLLM: Empowering Large Language Models for Data Analytics
CoddLLM, a Mistral-NeMo-12B model post-trained on synthetic analytics instruction data, outperforms GPT-4o on the paper's table-selection average and improves text-to-SQL over its base model, with the largest gains on...
-
What Really Matters for Table LLMs? A Meta-Evaluation of Model and Data Effects
By independently varying base models and training data across 12 models, this study shows that base model choice influences out-of-domain table task performance more than the instruction-tuning dataset does.
-
Does Table Source Matter? Benchmarking and Improving Multimodal Scientific Table Understanding and Reasoning
MMSci, a new scientific table benchmark and training set, shows that 52K domain-specific table images outperform 150K general-domain images for multimodal numerical reasoning.
-
Evaluating and Aligning CodeLLMs on Human Preference
A new 397-sample, 44-language code Q&A benchmark with LLM-judged human preference reveals gaps between open and proprietary code models and a 20B-token synthetic instruction corpus.
-
DataLab: A Unified Platform for LLM-Powered Business Intelligence
DataLab is a unified notebook-based platform for LLM-powered BI tasks that shows strong efficiency gains and competitive accuracy, but its state-of-the-art claim is not supported on several benchmarks.
-
FullStack Bench: Evaluating LLMs as Full Stack Coders
FullStack Bench and SandboxFusion offer a broader, execution-based benchmark for code LLMs with 3,374 problems in 16 languages and 11 domains.
-
TQA-Bench: Evaluating LLMs for Multi-Table Question Answering
TQA-Bench is a multi-table QA benchmark with 8K-64K contexts and symbolic question extensions; tests on 22 LLMs show accuracy declines with context length.
-
TableMind: An Autonomous Programmatic Agent for Tool-Augmented Table Reasoning
TableMind, a two-stage SFT-plus-RL agent trained on an 8B model, reports state-of-the-art results on three table reasoning benchmarks.
-
TableZoomer: A Collaborative Agent Framework for Large-scale Table Question Answering
TableZoomer compresses tables into schemas, zooms to query-relevant regions, and executes generated Python to answer questions, lifting Qwen3-8B accuracy by 19.34 points on DataBench and 25 points on TableBench Fact Checking.
-
TReB: A Comprehensive Benchmark for Evaluating Table Reasoning Capabilities of Large Language Models
TReB evaluates 26 large language models on 26 table reasoning subtasks using textual, programmatic, and interleaved reasoning modes, finding that the best model reaches only about 70 on a 0-100 judging scale.
-
Multimodal Tabular Reasoning with Privileged Structured Information
An 8B multimodal LLM trained on 9k reasoning traces distilled from structured tables reaches state-of-the-art open-source accuracy on table-image question answering and fact verification.
-
Zero-Shot Decision Tree Construction via Large Language Models
A prompt-based algorithm that constructs CART-style decision trees from feature descriptions alone, using LLM probability estimates instead of data.
-
Rethinking Table Instruction Tuning
A systematic hyperparameter study of table instruction tuning finds that small learning rates and 2,600 examples suffice, yielding TAMA, an 8B model competitive with GPT-3.5/GPT-4 on table benchmarks while keeping gen...
-
MRT at IberLEF-2025 PRESTA Task: Maximizing Recovery from Tables with Multiple Steps
MRT, an LLM code-generation pipeline for Spanish table QA, achieves 85% accuracy on the IberLEF 2025 PRESTA test set.
-
Towards High Supervised Learning Utility Training Data Generation: Data Pruning and Column Reordering
PRRO combines signal-based data pruning and column reordering to improve the supervised learning utility of synthetic tabular data, but its evaluation is undermined by data manipulation and an ill-defined correlation measure.
Discussion (0). Continue with ORCID to comment.