paper-with-me

홈 › Papers

Can LLMs Reason About Attention? Towards Zero-Shot Analysis of Multimodal Classroom Behavior

2026-04-03 · Nolan Platt, Sehrish Nizamani, Alp Tural, Elif Tural, Saad Nizamani, Andrew Katz, Yoonje Lee, Nada Basit arxiv

Understanding student engagement usually requires time-consuming manual observation or invasive recording that raises privacy concerns. We present a privacy-preserving pipeline that analyzes classroom videos to extract insights about student attention, without storing any identifiable footage. Our system runs on a single GPU, using OpenPose for skeletal extraction and Gaze-LLE for visual attention estimation. Original video frames are deleted immediately after pose extraction, thus only geometric coordinates (stored as JSON) are retained, ensuring compliance with FERPA. The extracted pose and gaze data is processed by QwQ-32B-Reasoning, which performs zero-shot analysis of student behavior across lecture segments. Instructors access results through a web dashboard featuring attention heatmaps and behavioral summaries. Our preliminary findings suggest that LLMs may show promise for multimodal behavior understanding, although they still struggle with spatial reasoning about classroom layouts. We discuss these limitations and outline directions for improving LLM spatial comprehension in educational analytics contexts.

📄 PDF Abstract BibTeX arXiv:2604.03401

Code (0)

등록된 구현이 없습니다.

Tasks

Spatial Reasoning

Similar Papers 제목 키워드 기반

Zero-Shot Chain-of-Thought Reasoning Guided by Evolutionary Algorithms in Large Language Models

2024-02-08 · Feihu Jin, Yifan Liu, Ying Tan

Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks and exhibited impressive reasoning abilities by applying zero-shot Chain-of-Thought (CoT) prompting. However, due to the evolving…

Evolutionary AlgorithmsSentence

Are LLMs Good Zero-Shot Fallacy Classifiers?

2024-10-19 · Fengjun Pan, Xiaobao Wu, Zongrui Li, Anh Tuan Luu

Fallacies are defective arguments with faulty reasoning. Detecting and classifying them is a crucial NLP task to prevent misinformation, manipulative claims, and biased decisions. However, existing fallacy classifiers ar…

Misinformation

Are Large Language Models Table-based Fact-Checkers?

2024-02-04 · Hanwen Zhang, Qingyi Si, Peng Fu, Zheng Lin 외

Table-based Fact Verification (TFV) aims to extract the entailment relation between statements and structured tables. Existing TFV methods based on small-scaled models suffer from insufficient labeled data and weak zero-…

Fact VerificationIn-Context LearningPrompt EngineeringTable-based Fact Verification

Exploring Failure Cases in Multimodal Reasoning About Physical Dynamics

2024-02-24 · Sadaf Ghaffari, Nikhil Krishnaswamy

In this paper, we present an exploration of LLMs' abilities to problem solve with physical reasoning in situated environments. We construct a simple simulated environment and demonstrate examples of where, in a zero-shot…

Language ModelingLanguage ModellingMultimodal ReasoningObject+1

What is an "Abstract Reasoner"? Revisiting Experiments and Arguments about Large Language Models

2025-07-30 · Tian Yun, Chen Sun, Ellie Pavlick arxiv

Recent work has argued that large language models (LLMs) are not "abstract reasoners", citing their poor zero-shot performance on a variety of challenging tasks as evidence. We revisit these experiments in order to add n…