UFEval: Unified Fine-grained Evaluation with Task and Aspect Generalization

• URL: http://arxiv.org/abs/2505.12795v3
• Date: Tue, 05 Aug 2025 06:17:42 GMT
• Title: UFEval: Unified Fine-grained Evaluation with Task and Aspect Generalization
• Authors: Shibo Hong, Jiahao Ying, Haiyuan Liang, Mengdi Zhang, Jun Kuang, Jiazheng Zhang, Yixin Cao,
• Abstract summary: UFEval is the first unified fine-grained evaluator with task and aspect generalization for four evaluation tasks.<n> FRABench is a large-scale, multi-modal, and aspect-level resource for training and testing evaluators.<n>Experiments show that learning on specific aspects enables UFEval to generalize to unseen aspects.
• Score: 7.416026808698028
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Evaluating the open-ended outputs of Large Multimodal Models has become a bottleneck as model capabilities, task diversity, and modality rapidly expand. Existing "LLM-as-a-Judge" evaluators are typically narrow in specific tasks and aspects. In this paper, we argue that, on one hand, based on the interconnected nature of aspects, learning specific aspects can generalize to unseen aspects; on the other hand, jointly learning to assess multiple visual aspects and tasks may foster a synergistic effect. To this end, we propose UFEval, the first unified fine-grained evaluator with task and aspect generalization for four evaluation tasks -- Natural Language Generation, Image Understanding, Image Generation, and Interleaved Text-and-Image Generation. Specifically, (1) We first construct a hierarchical aspect taxonomy encompassing 112 distinct aspects across the aforementioned four tasks. (2) Then, building upon this taxonomy, we create FRABench, a fine-grained evaluation dataset comprising 60.4k pairwise samples with 325k evaluation labels obtained from a combination of human and GPT-4o annotations. FRABench provides a large-scale, multi-modal, and aspect-level resource for training and testing evaluators. (3) Finally, leveraging FRABench, we develop UFEval, a unified fine-grained evaluator. Experiments show that learning on specific aspects enables UFEval to generalize to unseen aspects, and joint learning to assess diverse tasks and aspects can lead to substantial mutual benefits.

Related papers

• GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning [112.51671310005604]
  We present GLM-4.1V-9B-Thinking, a vision-language model (VLM) designed to advance general-purpose multimodal understanding and reasoning.<n>We propose Reinforcement Learning with Curriculum Sampling to unlock the full potential of the model.<n>Open-source GLM-4.1V-9B-Thinking achieves state-of-the-art performance among models of comparable size.
  arXiv  Detail & Related papers  (2025-07-01T17:55:04Z)
• VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement Learning [55.34552054232695]
  We introduce VisionReasoner, a unified framework capable of reasoning and solving multiple visual perception tasks.<n>We evaluate VisionReasoner on ten diverse tasks spanning three critical domains: detection, segmentation, and counting.
  arXiv  Detail & Related papers  (2025-05-17T16:51:47Z)
• Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation [38.20492321295552]
  Vision-Language Model (VLM) have gained widespread adoption in Open-Vocabulary (OV) object detection and segmentation tasks.<n>Despite they have shown promise on OV-related tasks, their effectiveness in conventional vision tasks has thus far been unevaluated.
  arXiv  Detail & Related papers  (2025-04-13T08:28:13Z)
• VOILA: Evaluation of MLLMs For Perceptual Understanding and Analogical Reasoning [63.0285363282581]
  Multimodal Large Language Models (MLLMs) have become a powerful tool for integrating visual and textual information.<n>We introduce VOILA, a benchmark designed to evaluate MLLMs' perceptual understanding and abstract relational reasoning.<n>We reveal that current MLLMs struggle to comprehend inter-image relationships and exhibit limited capabilities in high-level relational reasoning.
  arXiv  Detail & Related papers  (2025-02-25T23:36:19Z)
• EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents [63.43699771428243]
  EmbodiedBench is an extensive benchmark designed to evaluate vision-driven embodied agents.<n>We evaluated 19 leading proprietary and open-source MLLMs within EmbodiedBench.<n> MLLMs excel at high-level tasks but struggle with low-level manipulation.
  arXiv  Detail & Related papers  (2025-02-13T18:11:34Z)
• Automatic Evaluation for Text-to-image Generation: Task-decomposed Framework, Distilled Training, and Meta-evaluation Benchmark [62.58869921806019]
  We propose a task decomposition evaluation framework based on GPT-4o to automatically construct a new training dataset. We design innovative training strategies to effectively distill GPT-4o's evaluation capabilities into a 7B open-source MLLM, MiniCPM-V-2.6. Experimental results demonstrate that our distilled open-source MLLM significantly outperforms the current state-of-the-art GPT-4o-base baseline.
  arXiv  Detail & Related papers  (2024-11-23T08:06:06Z)
• Putting GPT-4o to the Sword: A Comprehensive Evaluation of Language, Vision, Speech, and Multimodal Proficiency [3.161954199291541]
  This research study comprehensively evaluates the language, vision, speech, and multimodal capabilities of GPT-4o. GPT-4o demonstrates high accuracy and efficiency across multiple domains in language and reasoning capabilities. The model shows variability and faces limitations in handling complex and ambiguous inputs.
  arXiv  Detail & Related papers  (2024-06-19T19:00:21Z)
• AlignMMBench: Evaluating Chinese Multimodal Alignment in Large Vision-Language Models [34.843603169616486]
  We introduce AlignMMBench, a benchmark for evaluating the alignment capabilities of large Vision-Language Models (VLMs)<n>This benchmark is meticulously curated from real-world scenarios and internet sources, and includes both single-turn and multi-turn dialogue scenarios.<n>We also develop CritiqueVLM, a rule-calibrated evaluator that exceeds GPT-4's evaluation ability.
  arXiv  Detail & Related papers  (2024-06-13T16:30:14Z)
• SEED-Bench-2: Benchmarking Multimodal Large Language Models [67.28089415198338]
  Multimodal large language models (MLLMs) have recently demonstrated exceptional capabilities in generating not only texts but also images given interleaved multimodal inputs. SEED-Bench-2 comprises 24K multiple-choice questions with accurate human annotations, which spans 27 dimensions. We evaluate the performance of 23 prominent open-source MLLMs and summarize valuable observations.
  arXiv  Detail & Related papers  (2023-11-28T05:53:55Z)
• GPT-4V(ision) as a Generalist Evaluator for Vision-Language Tasks [70.98062518872999]
  We validate GPT-4V's capabilities for evaluation purposes, addressing tasks ranging from foundational image-to-text and text-to-image synthesis to high-level image-to-image translations and multi-images to text alignment. Notably, GPT-4V shows promising agreement with humans across various tasks and evaluation methods, demonstrating immense potential for multi-modal LLMs as evaluators.
  arXiv  Detail & Related papers  (2023-11-02T16:11:09Z)
• MMBench: Is Your Multi-modal Model an All-around Player? [114.45702807380415]
  We propose MMBench, a benchmark for assessing the multi-modal capabilities of vision-language models. MMBench is meticulously curated with well-designed quality control schemes. MMBench incorporates multiple-choice questions in both English and Chinese versions.
  arXiv  Detail & Related papers  (2023-07-12T16:23:09Z)
• Towards a Unified Multi-Dimensional Evaluator for Text Generation [101.47008809623202]
  We propose a unified multi-dimensional evaluator UniEval for Natural Language Generation (NLG) We re-frame NLG evaluation as a Boolean Question Answering (QA) task, and by guiding the model with different questions, we can use one evaluator to evaluate from multiple dimensions. Experiments on three typical NLG tasks show that UniEval correlates substantially better with human judgments than existing metrics.
  arXiv  Detail & Related papers  (2022-10-13T17:17:03Z)
• Instruction Tuning for Few-Shot Aspect-Based Sentiment Analysis [72.9124467710526]
  generative approaches have been proposed to extract all four elements as (one or more) quadruplets from text as a single task. We propose a unified framework for solving ABSA, and the associated sub-tasks to improve the performance in few-shot scenarios.
  arXiv  Detail & Related papers  (2022-10-12T23:38:57Z)
• Multi-Task Learning for Dense Prediction Tasks: A Survey [87.66280582034838]
  Multi-task learning (MTL) techniques have shown promising results w.r.t. performance, computations and/or memory footprint. We provide a well-rounded view on state-of-the-art deep learning approaches for MTL in computer vision.
  arXiv  Detail & Related papers  (2020-04-28T09:15:50Z)

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.