Reasoning Limitations of Multimodal Large Language Models. A case study of Bongard Problems

• URL: http://arxiv.org/abs/2411.01173v1
• Date: Sat, 02 Nov 2024 08:06:30 GMT
• Title: Reasoning Limitations of Multimodal Large Language Models. A case study of Bongard Problems
• Authors: Mikołaj Małkiński, Szymon Pawlonka, Jacek Mańdziuk,
• Abstract summary: Bongard Problems (BPs) constitute a fundamental challenge in visual reasoning. multimodal large language models (MLLMs) inherently designed to combine vision and language are capable of tackling BPs. Experiments reveal significant limitations of MLLMs in solving BPs.
• Score: 0.0
• License:
• Abstract: Abstract visual reasoning (AVR) encompasses a suite of tasks whose solving requires the ability to discover common concepts underlying the set of pictures through an analogy-making process, similarly to human IQ tests. Bongard Problems (BPs), proposed in 1968, constitute a fundamental challenge in this domain mainly due to their requirement to combine visual reasoning and verbal description. This work poses a question whether multimodal large language models (MLLMs) inherently designed to combine vision and language are capable of tackling BPs. To this end, we propose a set of diverse MLLM-suited strategies to tackle BPs and examine four popular proprietary MLLMs: GPT-4o, GPT-4 Turbo, Gemini 1.5 Pro, and Claude 3.5 Sonnet, and four open models: InternVL2-8B, LLaVa-1.6 Mistral-7B, Phi-3.5-Vision, and Pixtral 12B. The above MLLMs are compared on three BP datasets: a set of original BP instances relying on synthetic, geometry-based images and two recent datasets based on real-world images, i.e., Bongard-HOI and Bongard-OpenWorld. The experiments reveal significant limitations of MLLMs in solving BPs. In particular, the models struggle to solve the classical set of synthetic BPs, despite their visual simplicity. Though their performance ameliorates on real-world concepts expressed in Bongard-HOI and Bongard-OpenWorld, the models still have difficulty in utilizing new information to improve their predictions, as well as utilizing a dialog context window effectively. To capture the reasons of performance discrepancy between synthetic and real-world AVR domains, we propose Bongard-RWR, a new BP dataset consisting of real-world images that translates concepts from hand-crafted synthetic BPs to real-world concepts. The MLLMs' results on Bongard-RWR suggest that their poor performance on classical BPs is not due to domain specificity but rather reflects their general AVR limitations.

Related papers

• HAMSTER: Hierarchical Action Models For Open-World Robot Manipulation [54.03004125910057]
  We show that hierarchical vision-language-action models can be more effective in utilizing off-domain data than standard monolithic VLA models. We show that, with the hierarchical design, the high-level VLM can transfer across significant domain gaps between the off-domain finetuning data and real-robot testing scenarios.
  arXiv  Detail & Related papers  (2025-02-08T07:50:22Z)
• Calling a Spade a Heart: Gaslighting Multimodal Large Language Models via Negation [65.92001420372007]
  This paper systematically evaluates state-of-the-art Multimodal Large Language Models (MLLMs) across diverse benchmarks. We show significant performance drops when negation arguments are introduced to initially correct responses.
  arXiv  Detail & Related papers  (2025-01-31T10:37:48Z)
• Sequential Compression Layers for Efficient Federated Learning in Foundational Models [2.6733991338938026]
  We propose a novel, simple, and more effective parameter-efficient fine-tuning method that does not rely on LoRA. This solution addresses the bottlenecks associated with LoRA in federated fine tuning and outperforms recent LoRA-based approaches.
  arXiv  Detail & Related papers  (2024-12-09T22:06:47Z)
• MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation? [59.7772329962047]
  We introduce MJ-Bench, a novel benchmark which incorporates a comprehensive preference dataset to evaluate multimodal judges. Specifically, we evaluate a large variety of multimodal judges including smaller-sized CLIP-based scoring models, open-source VLMs, and close-source VLMs. Experiments reveal that close-source VLMs generally provide better feedback, with GPT-4o outperforming other judges in average.
  arXiv  Detail & Related papers  (2024-07-05T20:03:16Z)
• Beyond Numeric Awards: In-Context Dueling Bandits with LLM Agents [25.825941077332182]
  This paper is the first to investigate Large Language Models (LLMs) as in-context decision-makers under the problem of Dueling Bandits (DB) We compare GPT-3.5 Turbo, GPT-4, GPT-4 Turbo, Llama 3.1, and o1-Preview against nine well-established DB algorithms. We show that our top-performing LLM, GPT-4 Turbo, has the zero-shot relative decision-making ability to achieve surprisingly low weak regret.
  arXiv  Detail & Related papers  (2024-07-02T02:18:14Z)
• VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks [10.266224162377371]
  Low-rank adaptation (LoRA) and its variants incur substantial storage and transmission costs. We introduce a "divide-and-share" paradigm that breaks the barriers of low-rank decomposition across matrix dimensions, modules, and layers. VB-LoRA achieves extreme parameter efficiency while maintaining comparable or better performance compared to state-of-the-art PEFT methods.
  arXiv  Detail & Related papers  (2024-05-24T03:24:34Z)
• Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models [73.40350756742231]
  Visually-conditioned language models (VLMs) have seen growing adoption in applications such as visual dialogue, scene understanding, and robotic task planning. Despite the volume of new releases, key design decisions around image preprocessing, architecture, and optimization are under-explored.
  arXiv  Detail & Related papers  (2024-02-12T18:21:14Z)
• Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World [57.832261258993526]
  Bongard-OpenWorld is a new benchmark for evaluating real-world few-shot reasoning for machine vision. It already imposes a significant challenge to current few-shot reasoning algorithms.
  arXiv  Detail & Related papers  (2023-10-16T09:19:18Z)
• LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models [55.304181390027274]
  This paper presents a comprehensive evaluation of publicly available large multimodal models by building a LVLM evaluation Hub (LVLM-eHub) Our LVLM-eHub consists of $8$ representative LVLMs such as InstructBLIP and MiniGPT-4, which are thoroughly evaluated by a quantitative capability evaluation and an online arena platform. The study reveals several innovative findings. First, instruction-tuned LVLM with massive in-domain data such as InstructBLIP heavily overfits many existing tasks, generalizing poorly in the open-world scenario.
  arXiv  Detail & Related papers  (2023-06-15T16:39:24Z)

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.