An Empirical Investigation of Robustness in Large Language Models under Tabular Distortions

• URL: http://arxiv.org/abs/2601.05009v1
• Date: Thu, 08 Jan 2026 15:10:32 GMT
• Title: An Empirical Investigation of Robustness in Large Language Models under Tabular Distortions
• Abstract summary: 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.
• Score: 8.023379679609151
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We investigate how large language models (LLMs) fail when tabular data in an otherwise canonical representation is subjected to semantic and structural distortions. Our findings reveal that LLMs lack an inherent ability to detect and correct subtle distortions in table representations. 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. To study this phenomenon, we introduce a small, expert-curated dataset that explicitly evaluates LLMs on table question answering (TQA) tasks requiring an additional error-correction step prior to analysis. Our results reveal systematic differences in how LLMs ingest and interpret tabular information under distortion, with even SoTA models such as GPT-5.2 model exhibiting a drop of minimum 22% accuracy under distortion. These findings raise important questions for future research, particularly regarding when and how models should autonomously decide to realign tabular inputs, analogous to human behavior, without relying on explicit prompts or tabular data pre-processing.

Related papers

• Why Large Language Models Fail at Tabular Prediction [1.1908340728628395]
  Large language models (LLMs) have become the default tool for a remarkable range of tasks.<n>But they have had conspicuously little success at one of the most common machine learning workloads.
  arXiv  Detail & Related papers  (2026-08-03T15:52:51Z)
• From Residuals to Reasons: LLM-Guided Mechanism Inference from Tabular Data [10.795877029195845]
  A persistent challenge in machine learning for scientific applications is jointly achieving prediction and understanding.<n>We introduce Multi-Agent Residual In-Context Learning (MARICL)<n>MARICL improves consistently over its base model on all datasets.
  arXiv  Detail & Related papers  (2026-05-21T15:34:08Z)
• The Power of Order: Fooling LLMs with Adversarial Table Permutations [49.84535222399142]
  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.
  arXiv  Detail & Related papers  (2026-05-01T06:25:55Z)
• When Words Change the Model: Sensitivity of LLMs for Constraint Programming Modelling [1.052782170493037]
  Large language models show impressive results in automatically generating models for classical benchmarks.<n>Many standard CP problems are likely included in the training data of these models.<n>We show that while LLMs can produce syntactically valid and semantically plausible models, their performance drops sharply under contextual and linguistic variation.
  arXiv  Detail & Related papers  (2025-11-18T10:40:32Z)
• Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences [16.09906989518837]
  We show that narrow finetuning creates strong biases in LLM activations that can be interpreted to understand the finetuning domain.<n>These biases can be discovered using simple tools from model diffing.<n>We demonstrate that these analyses contain crucial information by creating an LLM-based interpretability agent.
  arXiv  Detail & Related papers  (2025-10-14T19:05:59Z)
• Format as a Prior: Quantifying and Analyzing Bias in LLMs for Heterogeneous Data [17.88854327331652]
  Large Language Models (LLMs) are increasingly employed in applications that require processing information from heterogeneous formats.<n>This paper makes the first attempt to investigate and analyze the format bias in LLMs.<n>We identify three future research directions to reduce format bias: improving data preprocessing through format sanitization and normalization, introducing inference-time interventions such as attention re-weighting, and developing format-balanced training corpora.
  arXiv  Detail & Related papers  (2025-08-13T01:09:02Z)
• Protecting multimodal large language models against misleading visualizations [94.71976205962527]
  We show that questionanswering (QA) accuracy on misleading visualizations drops on average to the level of the random baseline.<n>We introduce the first inference-time methods to improve QA performance on misleading visualizations, without compromising accuracy on non-misleading ones.<n>We find that two methods, table-based QA and redrawing the visualization, are effective, with improvements of up to 19.6 percentage points.
  arXiv  Detail & Related papers  (2025-02-27T20:22:34Z)
• Error Classification of Large Language Models on Math Word Problems: A Dynamically Adaptive Framework [79.40678802098026]
  Math Word Problems serve as a crucial benchmark for evaluating Large Language Models' reasoning abilities.<n>Current error classification methods rely on static and predefined categories.<n>We propose Error-Aware Prompting (EAP) that incorporates common error patterns as explicit guidance.
  arXiv  Detail & Related papers  (2025-01-26T16:17:57Z)
• From Distributional to Overton Pluralism: Investigating Large Language Model Alignment [82.99849359892112]
  We re-examine previously reported reductions in response diversity post-alignment.<n>Our analysis suggests that an apparent drop in the diversity of responses is largely explained by quality control and information aggregation.<n>Findings indicate that current alignment techniques capture but do not extend the useful subset of assistant-like base LLM behavior.
  arXiv  Detail & Related papers  (2024-06-25T16:32:33Z)
• Low-rank finetuning for LLMs: A fairness perspective [54.13240282850982]
  Low-rank approximation techniques have become the de facto standard for fine-tuning Large Language Models. This paper investigates the effectiveness of these methods in capturing the shift of fine-tuning datasets from the initial pre-trained data distribution. We show that low-rank fine-tuning inadvertently preserves undesirable biases and toxic behaviors.
  arXiv  Detail & Related papers  (2024-05-28T20:43:53Z)
• Unleashing the Potential of Large Language Models for Predictive Tabular Tasks in Data Science [17.282770819829913]
  This research endeavors to apply Large Language Models (LLMs) towards addressing these predictive tasks.<n>Our research aims to mitigate this gap by compiling a comprehensive corpus of tables annotated with instructions and executing large-scale training of Llama-2.
  arXiv  Detail & Related papers  (2024-03-29T14:41:21Z)
• Interpretable Medical Diagnostics with Structured Data Extraction by Large Language Models [59.89454513692417]
  Tabular data is often hidden in text, particularly in medical diagnostic reports. We propose a novel, simple, and effective methodology for extracting structured tabular data from textual medical reports, called TEMED-LLM. We demonstrate that our approach significantly outperforms state-of-the-art text classification models in medical diagnostics.
  arXiv  Detail & Related papers  (2023-06-08T09:12:28Z)
• How Does Data Corruption Affect Natural Language Understanding Models? A Study on GLUE datasets [4.645287693363387]
  We show that performance remains high for most GLUE tasks when the models are fine-tuned or tested on corrupted data. Our proposed data transformations can be used as a diagnostic tool for assessing the extent to which a specific dataset constitutes a proper testbed for evaluating models' language understanding capabilities.
  arXiv  Detail & Related papers  (2022-01-12T13:35:53Z)
• Imputation-Free Learning from Incomplete Observations [73.15386629370111]
  We introduce the importance of guided gradient descent (IGSGD) method to train inference from inputs containing missing values without imputation. We employ reinforcement learning (RL) to adjust the gradients used to train the models via back-propagation. Our imputation-free predictions outperform the traditional two-step imputation-based predictions using state-of-the-art imputation methods.
  arXiv  Detail & Related papers  (2021-07-05T12:44:39Z)
• Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little [74.49773960145681]
  A possible explanation for the impressive performance of masked language model (MLM)-training is that such models have learned to represent the syntactic structures prevalent in NLP pipelines. In this paper, we propose a different explanation: pre-trains succeed on downstream tasks almost entirely due to their ability to model higher-order word co-occurrence statistics. Our results show that purely distributional information largely explains the success of pre-training, and underscore the importance of curating challenging evaluation datasets that require deeper linguistic knowledge.
  arXiv  Detail & Related papers  (2021-04-14T06:30:36Z)

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.