You May Speak Freely: Improving the Fine-Grained Visual Recognition Capabilities of Multimodal Large Language Models with Answer Extraction

• URL: http://arxiv.org/abs/2510.14885v1
• Date: Thu, 16 Oct 2025 17:04:25 GMT
• Title: You May Speak Freely: Improving the Fine-Grained Visual Recognition Capabilities of Multimodal Large Language Models with Answer Extraction
• Authors: Logan Lawrence, Oindrila Saha, Megan Wei, Chen Sun, Subhransu Maji, Grant Van Horn,
• Abstract summary: nlg2choice is a simple two-stage method which first asks the MLLM an open-ended question for the task with minimal constraints.<n>We compute the probability of the constrained response taking that choice with an early stopping method to significantly improve throughput.<n>Our results show improvement over a suite of seven fine-grained visual datasets when evaluating in terms of classification and retrieval.
• Score: 24.029138898778626
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite the renewed interest in zero-shot visual classification due to the rise of Multimodal Large Language Models (MLLMs), the problem of evaluating free-form responses of auto-regressive models remains a persistent challenge. Most existing works focus on language-only tasks or don't consider Multiple Choice Questions (MCQs) beyond 5-way options, both of which are critical capabilities to solve tasks in Fine-Grained Visual Classification (FGVC) where choice counts are in the hundreds to thousands and the choices are highly related. Furthermore, in this highly multi-way MCQ setting it is not clear how to extend LLM choice extraction to retrieval-based problems, where computing probabilities over the choice set is computationally costly. In this work we investigate nlg2choice, a simple two-stage method which first asks the MLLM an open-ended question for the task with minimal constraints, then uses text-only constrained decoding to predict the most likely choice. In retrieval settings, we compute the probability of the constrained response taking that choice with an early stopping method to significantly improve throughput. Our results show improvement over a suite of seven fine-grained visual datasets when evaluating in terms of classification and retrieval, and show that this performance holds over the various ways that users of LLMs can implement tasks in natural language.

Related papers

• Suffix-Constrained Greedy Search Algorithms for Causal Language Models [6.949966663998242]
  Large language models (LLMs) are powerful tools that have found applications beyond human-machine interfaces and chatbots.<n>Unfortunately, extracting the final answer in an LLM free-form output is difficult, as it is an information extraction problem on its own.<n>We introduce suffix- generation, that aims to produce well-constrained LLM responses in which final answers follow strict templates and are guaranteed to be trivially parseable.
  arXiv  Detail & Related papers  (2026-03-01T19:46:00Z)
• Right Answer, Wrong Score: Uncovering the Inconsistencies of LLM Evaluation in Multiple-Choice Question Answering [78.89231943329885]
  Multiple-Choice Question Answering (MCQA) is widely used to evaluate Large Language Models (LLMs)<n>We show that multiple factors can significantly impact the reported performance of LLMs.<n>We analyze whether existing answer extraction methods are aligned with human judgment.
  arXiv  Detail & Related papers  (2025-03-19T08:45:03Z)
• New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration [49.180693704510006]
  Referring Expression (REC) is a cross-modal task that evaluates the interplay of language understanding, image comprehension, and language-to-image grounding.<n>It serves as an essential testing ground for Multimodal Large Language Models (MLLMs)
  arXiv  Detail & Related papers  (2025-02-27T13:58:44Z)
• Option-ID Based Elimination For Multiple Choice Questions [12.30777266124562]
  Multiple choice questions (MCQs) are a popular and important task for evaluating large language models (LLMs)<n>This paper proposes a novel option-ID based PoE ($textPoE_textID$)
  arXiv  Detail & Related papers  (2025-01-25T11:06:37Z)
• Large Vision-Language Models for Remote Sensing Visual Question Answering [0.0]
  Remote Sensing Visual Question Answering (RSVQA) is a challenging task that involves interpreting complex satellite imagery to answer natural language questions. Traditional approaches often rely on separate visual feature extractors and language processing models, which can be computationally intensive and limited in their ability to handle open-ended questions. We propose a novel method that leverages a generative Large Vision-Language Model (LVLM) to streamline the RSVQA process.
  arXiv  Detail & Related papers  (2024-11-16T18:32:38Z)
• FSM: A Finite State Machine Based Zero-Shot Prompting Paradigm for Multi-Hop Question Answering [26.398873686905063]
  Large Language Models (LLMs) with chain-of-thought (COT) prompting have demonstrated impressive abilities on simple nature language inference tasks. We propose a prompting method, Finite State Machine (FSM) to enhance the reasoning capabilities of LLM for complex tasks.
  arXiv  Detail & Related papers  (2024-07-03T10:01:01Z)
• UnibucLLM: Harnessing LLMs for Automated Prediction of Item Difficulty and Response Time for Multiple-Choice Questions [25.877058354902953]
  This work explores a novel data augmentation method based on Large Language Models (LLMs) for predicting item difficulty and response time of retired USMLE Multiple-Choice Questions (MCQs) in the BEA 2024 Shared Task. Our approach is based on augmenting the dataset with answers from zero-shot LLMs and employing transformer-based models based on six alternative feature combinations.
  arXiv  Detail & Related papers  (2024-04-20T10:41:02Z)
• Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems [76.69936664916061]
  We study how the number of LM calls affects the performance of Vote and Filter-Vote. We find, surprisingly, that across multiple language tasks, the performance of both Vote and Filter-Vote can first increase but then decrease as a function of the number of LM calls.
  arXiv  Detail & Related papers  (2024-03-04T19:12:48Z)
• LLMs May Perform MCQA by Selecting the Least Incorrect Option [29.202758753639078]
  Large Language Models (LLMs) have markedly enhanced performance across a variety of tasks.<n>The adoption of Multiple Choice Question Answering (MCQA) as a benchmark for assessing LLMs has gained considerable traction.<n>However, concerns regarding the robustness of this evaluative method persist.
  arXiv  Detail & Related papers  (2024-02-02T12:07:00Z)
• SEMQA: Semi-Extractive Multi-Source Question Answering [94.04430035121136]
  We introduce a new QA task for answering multi-answer questions by summarizing multiple diverse sources in a semi-extractive fashion. We create the first dataset of this kind, QuoteSum, with human-written semi-extractive answers to natural and generated questions.
  arXiv  Detail & Related papers  (2023-11-08T18:46:32Z)
• Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models [69.59125732317972]
  We propose a simple yet effective Retrieving-to-Answer (R2A) framework for VideoQA. R2A first retrieves a set of semantically similar texts from a generic text corpus using a pre-trained multi-modal model. With both the question and the retrieved texts, a LLM can be directly used to yield a desired answer.
  arXiv  Detail & Related papers  (2023-06-15T20:56:20Z)
• From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Models [111.42052290293965]
  Large language models (LLMs) have demonstrated excellent zero-shot generalization to new language tasks. End-to-end training on vision and language data may bridge the disconnections, but is inflexible and computationally expensive. We propose emphImg2Prompt, a plug-and-play module that provides the prompts that can bridge the aforementioned modality and task disconnections.
  arXiv  Detail & Related papers  (2022-12-21T08:39:36Z)
• Leveraging Large Language Models for Multiple Choice Question Answering [6.198523595657983]
  We show that a model with high MCSB ability performs much better with the natural approach than with the traditional approach. We show that a model with high MCSB ability performs much better with the natural approach than with the traditional approach.
  arXiv  Detail & Related papers  (2022-10-22T05:04:54Z)

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.