paper-with-me

홈 › Papers

Learning to Correction: Explainable Feedback Generation for Visual Commonsense Reasoning Distractor

2024-12-08 · Jiali Chen, Xusen Hei, Yuqi Xue, Yuancheng Wei, Jiayuan Xie, Yi Cai, Qing Li

Large multimodal models (LMMs) have shown remarkable performance in the visual commonsense reasoning (VCR) task, which aims to answer a multiple-choice question based on visual commonsense within an image. However, the ability of LMMs to correct potential visual commonsense errors in the distractor upon their occurrence is yet under-explored. Drawing inspiration from how a human teacher crafts challenging distractors to test students' comprehension of the concepts or skills and assists them in identifying and correcting errors toward the answer, we are the pioneering research for LMMs to simulate this error correction process. To this end, we employ GPT-4 as a ``teacher'' to collect the explainable feedback dataset VCR-DF for error correction, which serves as a benchmark to evaluate the ability of LMMs to identify misconceptions and clarify reasons behind the error in VCR distractors toward final answers. In addition, we propose an LMM-based Pedagogical Expert Instructed Feedback Generation (PEIFG) model to incorporate the learnable expert prompts and multimodal instruction as guidance for feedback generation. Experimental results show that our PEIFG significantly outperforms existing LMMs. We believe that our benchmark provides a new direction for evaluating the capabilities of LMMs.

📄 PDF Abstract BibTeX arXiv:2412.07801

Code (1)

gary-code/peifg 공식 구현 pytorch

Tasks

MisconceptionsMultiple-choiceVisual Commonsense Reasoning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Adam 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Position-Wise Feed-Forward Layer 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

INSTRUCTSCORE: Explainable Text Generation Evaluation with Finegrained Feedback

2023-05-23 · Wenda Xu, Danqing Wang, Liangming Pan, Zhenqiao Song 외

Automatically evaluating the quality of language generation is critical. Although recent learned metrics show high correlation with human judgement, these metrics can not explain their verdict or associate the scores wit…

DiagnosticText Generation

VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation

2025-06-04 · Yuansheng Ni, Ping Nie, Kai Zou, Xiang Yue 외

Large language models (LLMs) often struggle with visualization tasks like plotting diagrams, charts, where success depends on both code correctness and visual semantics. Existing instruction-tuning datasets lack executio…

Code Generation

DIVE: Towards Descriptive and Diverse Visual Commonsense Generation

2024-08-15 · Jun-Hyung Park, Hyuntae Park, Youjin Kang, Eojin Jeon 외

Towards human-level visual understanding, visual commonsense generation has been introduced to generate commonsense inferences beyond images. However, current research on visual commonsense generation has overlooked an i…

DescriptiveDiversity

RefineSVG: Visual Feedback-Driven Reinforcement Learning for Image-to-SVG Generation

2026-07-30 · Shaobo Liu, Feiqiao Mao, Shuaishuai Zhou, Yan Zhan 외 arxiv

We propose RefineSVG, a single-step closed-loop visual feedback framework that enables multimodal large language models (MLLMs) to perform high-fidelity image-to-SVG generation through self-correction. Existing MLLM-base…

Reinforcement Learning

What Makes The Story Forward? Inferring Commonsense Explanations as Prompts for Future Event Generation

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Future Event Generation (FEG) aims to generate fluent and reasonable future event descriptions given preceding events. It requires not only fluent text generation but also commonsense reasoning to maintain the coherence …

Text Generation