The Power of Order: Fooling LLMs with Adversarial Table Permutations

• URL: http://arxiv.org/abs/2605.00445v2
• Date: Wed, 06 May 2026 06:39:15 GMT
• Title: The Power of Order: Fooling LLMs with Adversarial Table Permutations
• Abstract summary: Adversarial Table Permutation is a gradient-based attack that efficiently identifies worst-case permutations designed to maximally disrupt model performance.<n>Our experiments demonstrate that ATP significantly degrades the performance of a wide range of LLMs.<n>Our findings expose a fundamental weakness in how current LLMs process structured data, underscoring the urgent need to develop permutation-robust models for reliable, real-world applications.
• Score: 49.84535222399142
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models have achieved remarkable success and are increasingly deployed in critical applications involving tabular data, such as Table Question Answering. However, their robustness to the structure of this input remains a critical, unaddressed question. This paper demonstrates that modern LLMs exhibit a significant vulnerability to the layout of tabular data. Specifically, we show that semantically-invariant permutations of rows and columns - rearrangements that do not alter the table's underlying information - are sometimes sufficient to cause incorrect or inconsistent model outputs. To systematically probe this vulnerability, we introduce Adversarial Table Permutation, a novel, gradient-based attack that efficiently identifies worst-case permutations designed to maximally disrupt model performance. Our extensive experiments demonstrate that ATP significantly degrades the performance of a wide range of LLMs. This reveals a pervasive vulnerability across different model sizes and architectures, including the most recent and popular models. Our findings expose a fundamental weakness in how current LLMs process structured data, underscoring the urgent need to develop permutation-robust models for reliable, real-world applications.

Related papers

• An Empirical Investigation of Robustness in Large Language Models under Tabular Distortions [8.023379679609151]
  Large language models (LLMs) fail when tabular data in an otherwise canonical representation is subjected to semantic and structural distortions.<n>Only when provided with an explicit prior, via a system prompt, do models partially adjust their reasoning strategies and correct some distortions, though not consistently or completely.
  arXiv  Detail & Related papers  (2026-01-08T15:10:32Z)
• Table as a Modality for Large Language Models [28.392792653645998]
  We show a probing experiment on our proposed StructQA benchmark.<n>We propose TAMO, which bears an ideology to treat the tables as an independent modality integrated with the text tokens.
  arXiv  Detail & Related papers  (2025-11-30T15:59:56Z)
• TableZoomer: A Collaborative Agent Framework for Large-scale Table Question Answering [26.00027389659854]
  TableZoomer is a programming-based agent framework for the table question answering (TQA) task.<n>It introduces three key innovations: (1) replacing the original fully verbalized table with structured table schema to bridge the semantic gap and reduce computational complexity; (2) a query-aware table zooming mechanism that dynamically generates sub-table schema through column selection and entity linking; and (3) a Program-of-Thoughts (PoT) strategy that transforms queries into executable code to mitigate numerical hallucination.
  arXiv  Detail & Related papers  (2025-09-01T09:53:01Z)
• LLM-Symbolic Integration for Robust Temporal Tabular Reasoning [69.27153114778748]
  We introduce TempTabQA-C, a synthetic dataset designed for systematic and controlled evaluations.<n>This structured approach allows Large Language Models (LLMs) to generate and executesql queries, enhancing generalization and mitigating biases.
  arXiv  Detail & Related papers  (2025-06-06T05:14:04Z)
• Multimodal Tabular Reasoning with Privileged Structured Information [67.40011423365712]
  We introduce TabUlar Reasoning with Bridged infOrmation (sc Turbo)<n>sc Turbo benefits from a structure-aware reasoning trace generator based on DeepSeek-R1.<n>sc Turbo achieves state-of-the-art performance ($+7.2%$ vs. previous SOTA) across multiple datasets.
  arXiv  Detail & Related papers  (2025-06-04T15:46:30Z)
• TableLoRA: Low-rank Adaptation on Table Structure Understanding for Large Language Models [57.005158277893194]
  TableLoRA is a module designed to improve LLMs' understanding of table structure during PEFT.<n>It incorporates special tokens for serializing tables with special token encoder and uses 2D LoRA to encode low-rank information on cell positions.
  arXiv  Detail & Related papers  (2025-03-06T12:50:14Z)
• 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)
• 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)
• HeLM: Highlighted Evidence augmented Language Model for Enhanced Table-to-Text Generation [7.69801337810352]
  We conduct parameter-efficient fine-tuning on the LLaMA2 model. Our approach involves injecting reasoning information into the input by emphasizing table-specific row data. On both the FetaQA and QTSumm datasets, our approach achieved state-of-the-art results.
  arXiv  Detail & Related papers  (2023-11-15T12:02:52Z)

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.