REVIEW 9 cited by
TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios
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
read the original abstract
We introduce TableLLM, a robust large language model (LLM) with 8 billion parameters, purpose-built for proficiently handling tabular data manipulation tasks, whether they are embedded within documents or spreadsheets, catering to real-world office scenarios. We propose a distant supervision method for training, which comprises a reasoning process extension strategy, aiding in training LLMs to understand reasoning patterns more effectively as well as a cross-way validation strategy, ensuring the quality of the automatically generated data. To evaluate the performance of TableLLM, we have crafted benchmarks tailored to address both document and spreadsheet formats as well as constructed a well-organized evaluation pipeline capable of handling both scenarios. Thorough evaluations underscore the advantages of TableLLM when compared to various existing general-purpose and tabular data-focused LLMs. We have publicly released the model checkpoint, source code, benchmarks, and a web application for user interaction. Our codes and data are publicly available at https://github.com/TableLLM/TableLLM.
Forward citations
Cited by 9 Pith papers
-
AraTable: Benchmarking LLMs' Reasoning and Understanding of Arabic Tabular Data
AraTable is the first Arabic tabular QA benchmark; its experiments show LLMs are much weaker at reasoning over Arabic tables than at direct lookup.
-
Table Understanding and (Multimodal) LLMs: A Cross-Domain Case Study on Scientific vs. Non-Scientific Data
A new benchmark, TableEval, with 3017 tables in five formats, shows LLMs are robust to table representation but perform worse on scientific tables, with the caveat that the domain gap is confounded by task difficulty.
-
Atomic Reasoning for Scientific Table Claim Verification
Fine-tuning LLMs on 350 atomic reasoning examples improves scientific table claim verification, but the claimed edge over GPT-4o CoT only appears on the public SciTab benchmark.
-
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.
-
TableCopilot: A Table Assistant Empowered by Natural Language Conditional Table Discovery
A new task and system for finding unionable or joinable tables that satisfy a user's natural language condition, evaluated on a new benchmark.
-
Towards Benchmarking Foundation Models for Tabular Data With Text
A new 13-dataset benchmark shows that adding text embeddings to tabular models usually improves accuracy, but no embedding or downsampling strategy dominates.
-
Text to Query Plans for Question Answering on Large Tables
A ReAct-style LLM agent converts natural-language questions into query plans over DataFrame operators, using a three-level column-cluster-table vector index to handle tables with over 8,000 columns.
-
Schema-R1: A reasoning training approach for schema linking in Text-to-SQL Task
Schema-R1 combines cold-start SFT on 200 CoT samples with GRPO rule-based RL, reporting table and column filter accuracy gains of 10 percentage points or more over a fine-tuned baseline on Spider-dev.
Discussion (0). Sign in to comment.