paper-with-me

Papers

ReForm-Eval: Evaluating Large Vision Language Models via Unified Re-Formulation of Task-Oriented Benchmarks

2023-10-04 · Zejun Li, Ye Wang, Mengfei Du, Qingwen Liu, Binhao Wu, Jiwen Zhang, Chengxing Zhou, Zhihao Fan, Jie Fu, Jingjing Chen, Xuanjing Huang, Zhongyu Wei

Recent years have witnessed remarkable progress in the development of large vision-language models (LVLMs). Benefiting from the strong language backbones and efficient cross-modal alignment strategies, LVLMs exhibit surprising capabilities to perceive visual signals and perform visually grounded reasoning. However, the capabilities of LVLMs have not been comprehensively and quantitatively evaluate. Most existing multi-modal benchmarks require task-oriented input-output formats, posing great challenges to automatically assess the free-form text output of LVLMs. To effectively leverage the annotations available in existing benchmarks and reduce the manual effort required for constructing new benchmarks, we propose to re-formulate existing benchmarks into unified LVLM-compatible formats. Through systematic data collection and reformulation, we present the ReForm-Eval benchmark, offering substantial data for evaluating various capabilities of LVLMs. Based on ReForm-Eval, we conduct extensive experiments, thoroughly analyze the strengths and weaknesses of existing LVLMs, and identify the underlying factors. Our benchmark and evaluation framework will be open-sourced as a cornerstone for advancing the development of LVLMs.

📄 PDF Abstract BibTeX arXiv:2310.02569

Code (1)

fudandisc/reform-eval 공식 구현 pytorch

Tasks

cross-modal alignment

Similar Papers 제목 키워드 기반

CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption

2026-02-02 · Hanjun Park, Byeongseo Min, Jiheon Woo, Min-Wook Jeong 외 arxiv

Homomorphic encryption (HE) is a prominent framework for privacy-preserving machine learning, enabling inference directly on encrypted data. However, evaluating softmax, a core component of transformer architectures, rem…

Large Language Models Could Be Rote Learners

2025-04-11 · Yuyang Xu, Renjun Hu, Haochao Ying, Jian Wu 외

Multiple-choice question (MCQ) benchmarks are widely used for evaluating Large Language Models (LLMs), yet their reliability is undermined by benchmark contamination. In this study, we reframe contamination as an inheren…

MemorizationMMLUMultiple-choice

Controlled Reformulation Testing for Logical Consistency in Large Language Models

2026-07-16 · Alexander Gu, Alan Chen arxiv

Large language models (LLMs) frequently contradict themselves when the surface form of a logically equivalent question changes. We present a benchmark of 350 question families (1,750 total questions) for Controlled Refor…

Logical Reasoning

Reformulation for Pretraining Data Augmentation

2025-02-06 · Xintong Hao, Ruijie Zhu, Ge Zhang, Ke Shen 외

Despite the impressive capabilities of large language models across various tasks, their continued scaling is severely hampered not only by data scarcity but also by the performance degradation associated with excessive …

Data AugmentationPrompt Engineering

CoFL: Continuous Flow Fields for Language-Conditioned Navigation

2026-03-03 · Haokun Liu, Zhaoqi Ma, Yicheng Chen, Masaki Kitagawa 외 arxiv

Existing language-conditioned navigation systems typically rely on modular pipelines or trajectory generators, but the latter use each scene--instruction annotation mainly to supervise one start-conditioned rollout. To a…

Trajectory Prediction