Protecting multimodal large language models against misleading visualizations

• URL: http://arxiv.org/abs/2502.20503v3
• Date: Sun, 27 Apr 2025 11:32:57 GMT
• Title: Protecting multimodal large language models against misleading visualizations
• Authors: Jonathan Tonglet, Tinne Tuytelaars, Marie-Francine Moens, Iryna Gurevych,
• Abstract summary: We introduce the first inference-time methods to improve performance on misleading visualizations.<n>We find that MLLM question-answering accuracy drops on average to the level of a random baseline.
• Score: 94.71976205962527
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Visualizations play a pivotal role in daily communication in an increasingly data-driven world. Research on multimodal large language models (MLLMs) for automated chart understanding has accelerated massively, with steady improvements on standard benchmarks. However, for MLLMs to be reliable, they must be robust to misleading visualizations, charts that distort the underlying data, leading readers to draw inaccurate conclusions that may support disinformation. Here, we uncover an important vulnerability: MLLM question-answering accuracy on misleading visualizations drops on average to the level of a random baseline. To address this, we introduce the first inference-time methods to improve performance on misleading visualizations, without compromising accuracy on non-misleading ones. The most effective method extracts the underlying data table and uses a text-only LLM to answer the question based on the table. Our findings expose a critical blind spot in current research and establish benchmark results to guide future efforts in reliable MLLMs.

Related papers

• Unmasking Deceptive Visuals: Benchmarking Multimodal Large Language Models on Misleading Chart Question Answering [28.54154468156412]
  Misleading chart visualizations can distort perceptions and lead to incorrect conclusions. Recent advances in large language models (MLLMs) have demonstrated strong chart comprehension capabilities. This paper introduces the Misleading Chart Question Answering (Misleading ChartQA) Benchmark, a large-scale dataset designed to assess MLLMs in identifying and reasoning about misleading charts.
  arXiv  Detail & Related papers  (2025-03-23T18:56:33Z)
• Forget What You Know about LLMs Evaluations - LLMs are Like a Chameleon [11.753349115726952]
  Large language models (LLMs) often appear to excel on public benchmarks, but these high scores may mask an overreliance on dataset-specific surface cues. We introduce the Chameleon Benchmark Overfit Detector (C-BOD), a meta-evaluation framework that distorts benchmark prompts. By rephrasing inputs while preserving semantic content and labels, C-BOD exposes whether a model's performance is driven by memorized patterns.
  arXiv  Detail & Related papers  (2025-02-11T10:43:36Z)
• Epistemic Integrity in Large Language Models [11.173637560124828]
  Large language models are increasingly relied upon sources of information, but their propensity for false or misleading statements poses high risks for users and society. In this paper, we confront the critical problem of miscalibration where a model's linguistic assertiveness fails to reflect its true internal certainty. We introduce a new human misalignment evaluation and a novel method for measuring the linguistic assertiveness of Large Language Models.
  arXiv  Detail & Related papers  (2024-11-10T17:10:13Z)
• Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarios [16.47255259608715]
  Existing benchmarks require even 5-15 response attempts per sample to assess uncertainty. We propose a two-stage pipeline: first, we collect MLLMs' responses without misleading information, and then gather misleading ones via specific misleading instructions. Our experiments reveal that all open-source and close-source MLLMs are highly susceptible to misleading instructions, with an average misleading rate exceeding 86%.
  arXiv  Detail & Related papers  (2024-11-05T01:11:28Z)
• Context is Key: A Benchmark for Forecasting with Essential Textual Information [87.3175915185287]
  "Context is Key" (CiK) is a forecasting benchmark that pairs numerical data with diverse types of carefully crafted textual context. We evaluate a range of approaches, including statistical models, time series foundation models, and LLM-based forecasters. We propose a simple yet effective LLM prompting method that outperforms all other tested methods on our benchmark.
  arXiv  Detail & Related papers  (2024-10-24T17:56:08Z)
• Are LLMs Better than Reported? Detecting Label Errors and Mitigating Their Effect on Model Performance [21.926934384262594]
  Large language models (LLMs) offer new opportunities to enhance the annotation process. We compare expert, crowd-sourced, and our LLM-based annotations in terms of agreement, label quality, and efficiency. Our findings reveal a substantial number of label errors, which, when corrected, induce a significant upward shift in reported model performance.
  arXiv  Detail & Related papers  (2024-10-24T16:27:03Z)
• A Comparative Study of Translation Bias and Accuracy in Multilingual Large Language Models for Cross-Language Claim Verification [1.566834021297545]
  This study systematically evaluates translation bias and the effectiveness of Large Language Models for cross-lingual claim verification. We investigate two distinct translation methods: pre-translation and self-translation. Our findings reveal that low-resource languages exhibit significantly lower accuracy in direct inference due to underrepresentation.
  arXiv  Detail & Related papers  (2024-10-14T09:02:42Z)
• SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning [70.21358720599821]
  Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts. We propose SELF-GUIDE, a multi-stage mechanism in which we synthesize task-specific input-output pairs from the student LLM. We report an absolute improvement of approximately 15% for classification tasks and 18% for generation tasks in the benchmark's metrics.
  arXiv  Detail & Related papers  (2024-07-16T04:41:58Z)
• MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs [38.93090238335506]
  Spurious bias, a tendency to use spurious correlations between non-essential input attributes and target variables for predictions, has revealed a severe pitfall in deep learning models trained on single modality data. We introduce MM-SpuBench, a comprehensive visual question-answering (VQA) benchmark designed to evaluate MLLMs' reliance on nine distinct categories of spurious correlations. Our findings illuminate the persistence of the reliance on spurious correlations from these models and underscore the urge for new methodologies to mitigate spurious biases.
  arXiv  Detail & Related papers  (2024-06-24T20:29:16Z)
• CaLM: Contrasting Large and Small Language Models to Verify Grounded Generation [76.31621715032558]
  Grounded generation aims to equip language models (LMs) with the ability to produce more credible and accountable responses. We introduce CaLM, a novel verification framework. Our framework empowers smaller LMs, which rely less on parametric memory, to validate the output of larger LMs.
  arXiv  Detail & Related papers  (2024-06-08T06:04:55Z)
• Advancing Anomaly Detection: Non-Semantic Financial Data Encoding with LLMs [49.57641083688934]
  We introduce a novel approach to anomaly detection in financial data using Large Language Models (LLMs) embeddings. Our experiments demonstrate that LLMs contribute valuable information to anomaly detection as our models outperform the baselines.
  arXiv  Detail & Related papers  (2024-06-05T20:19:09Z)
• Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding [78.36702055076456]
  This paper introduces Multi-scale Positional. (Ms-PoE) which is a simple yet effective plug-and-play approach to enhance the capacity of. LLMs to handle relevant information located in the middle of the context.
  arXiv  Detail & Related papers  (2024-03-05T04:58:37Z)
• Probing LLMs for hate speech detection: strengths and vulnerabilities [8.626059038321724]
  We utilise different prompt variation, input information and evaluate large language models in zero shot setting. We select three large language models (GPT-3.5, text-davinci and Flan-T5) and three datasets - HateXplain, implicit hate and ToxicSpans. We find that on average including the target information in the pipeline improves the model performance substantially.
  arXiv  Detail & Related papers  (2023-10-19T16:11:02Z)
• POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained models [62.23255433487586]
  We propose an unsupervised fine-tuning framework to fine-tune the model or prompt on the unlabeled target data. We demonstrate how to apply our method to both language-augmented vision and masked-language models by aligning the discrete distributions extracted from the prompts and target data.
  arXiv  Detail & Related papers  (2023-04-29T22:05:22Z)
• Debiasing Vision-Language Models via Biased Prompts [79.04467131711775]
  We propose a general approach for debiasing vision-language foundation models by projecting out biased directions in the text embedding. We show that debiasing only the text embedding with a calibrated projection matrix suffices to yield robust classifiers and fair generative models.
  arXiv  Detail & Related papers  (2023-01-31T20:09:33Z)
• A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning [55.96577490779591]
  Vision-language models can encode societal biases and stereotypes. There are challenges to measuring and mitigating these multimodal harms. We investigate bias measures and apply ranking metrics for image-text representations.
  arXiv  Detail & Related papers  (2022-03-22T17:59:04Z)
• Distributionally Robust Multilingual Machine Translation [94.51866646879337]
  We propose a new learning objective for Multilingual neural machine translation (MNMT) based on distributionally robust optimization. We show how to practically optimize this objective for large translation corpora using an iterated best response scheme. Our method consistently outperforms strong baseline methods in terms of average and per-language performance under both many-to-one and one-to-many translation settings.
  arXiv  Detail & Related papers  (2021-09-09T03:48:35Z)

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.