Pith. sign in

REVIEW 5 cited by

Tables as Texts or Images: Evaluating the Table Reasoning Ability of LLMs and MLLMs

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2402.12424 v5 pith:PUTNWKP5 submitted 2024-02-19 cs.LG cs.AIcs.CLcs.CV

Naihao Deng , Zhenjie Sun , Ruiqi He , Aman Sikka , Yulong Chen , Lin Ma , Yue Zhang , Rada Mihalcea This is my paper · ORCID
classification cs.LGcs.AIcs.CLcs.CV
keywords llmstabledataimage-basedperformancepromptingrepresentationstable-related
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In this paper, we investigate the effectiveness of various LLMs in interpreting tabular data through different prompting strategies and data formats. Our analyses extend across six benchmarks for table-related tasks such as question-answering and fact-checking. We introduce for the first time the assessment of LLMs' performance on image-based table representations. Specifically, we compare five text-based and three image-based table representations, demonstrating the role of representation and prompting on LLM performance. Our study provides insights into the effective use of LLMs on table-related tasks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Chumor 2.0: Towards Benchmarking Chinese Humor Understanding

    cs.CL 2024-12 conditional novelty 7.0 of 10

    Chumor is a new Chinese humor explanation benchmark where LLMs perform near chance (best accuracy 60.3%) and well below human accuracy (78.3%).

  2. MTabVQA: Evaluating Multi-Tabular Reasoning of Language Models in Visual Space

    cs.CV 2025-06 conditional novelty 6.0 of 10

    MTabVQA is a new visual multi-table question answering benchmark, and fine-tuning VLMs on its instruction set improves their accuracy on it.

  3. TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuning

    cs.CL 2025-06 conditional novelty 6.0 of 10

    An iterative, weakness-guided data synthesis framework for table instruction tuning improves Llama3.1-8B by 11.6 average accuracy points using only 27K synthetic examples.

  4. GeoGrid-Bench: Can Foundation Models Understand Multimodal Gridded Geo-Spatial Data?

    cs.CL 2025-05 conditional novelty 6.0 of 10

    GeoGrid-Bench evaluates 11 foundation models on 3,200 expert-curated questions about gridded climate data across 16 variables, finding vision-language models strongest and code generation weakest.

  5. VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation

    cs.CL 2024-12 conditional novelty 6.0 of 10

    VisDoMRAG runs separate text and image retrieval and reasoning streams, fuses them with an LLM consistency check, and the authors release a multi-document benchmark with visually rich content.

Pith tools