Leveraging LLMs with Iterative Loop Structure for Enhanced Social Intelligence in Video Question Answering

• URL: http://arxiv.org/abs/2503.21190v1
• Date: Thu, 27 Mar 2025 06:14:21 GMT
• Title: Leveraging LLMs with Iterative Loop Structure for Enhanced Social Intelligence in Video Question Answering
• Authors: Erika Mori, Yue Qiu, Hirokatsu Kataoka, Yoshimitsu Aoki,
• Abstract summary: Social intelligence is essential for effective communication and adaptive responses.<n>Current video-based methods for social intelligence rely on general video recognition or emotion recognition techniques.<n>We propose the Looped Video Debating framework, which integrates Large Language Models with visual information.
• Score: 13.775516653315103
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Social intelligence, the ability to interpret emotions, intentions, and behaviors, is essential for effective communication and adaptive responses. As robots and AI systems become more prevalent in caregiving, healthcare, and education, the demand for AI that can interact naturally with humans grows. However, creating AI that seamlessly integrates multiple modalities, such as vision and speech, remains a challenge. Current video-based methods for social intelligence rely on general video recognition or emotion recognition techniques, often overlook the unique elements inherent in human interactions. To address this, we propose the Looped Video Debating (LVD) framework, which integrates Large Language Models (LLMs) with visual information, such as facial expressions and body movements, to enhance the transparency and reliability of question-answering tasks involving human interaction videos. Our results on the Social-IQ 2.0 benchmark show that LVD achieves state-of-the-art performance without fine-tuning. Furthermore, supplementary human annotations on existing datasets provide insights into the model's accuracy, guiding future improvements in AI-driven social intelligence.

Related papers

• A Human Digital Twin Architecture for Knowledge-based Interactions and Context-Aware Conversations [0.9580312063277943]
  Recent developments in Artificial Intelligence (AI) and Machine Learning (ML) are creating new opportunities for Human-Autonomy Teaming (HAT) We present a real-time Human Digital Twin (HDT) architecture that integrates Large Language Models (LLMs) for knowledge reporting, answering, and recommendation, embodied in a visual interface. The HDT acts as a visually and behaviorally realistic team member, integrated throughout the mission lifecycle, from training to deployment to after-action review.
  arXiv  Detail & Related papers  (2025-04-04T03:56:26Z)
• MimeQA: Towards Socially-Intelligent Nonverbal Foundation Models [27.930709161679424]
  We tap into data rich in nonverbal and social interactions -- mime videos.<n>We evaluate state-of-the-art video large language models (vLLMs) and find that their overall accuracy ranges from 15-30%.<n>Our analysis reveals that vLLMs often fail to ground imagined objects and over-rely on the text prompt while ignoring subtle nonverbal interactions.
  arXiv  Detail & Related papers  (2025-02-23T18:05:49Z)
• HumanVBench: Exploring Human-Centric Video Understanding Capabilities of MLLMs with Synthetic Benchmark Data [55.739633494946204]
  We present HumanVBench, an innovative benchmark meticulously crafted to bridge gaps in the evaluation of video MLLMs.<n>HumanVBench comprises 16 carefully designed tasks that explore two primary dimensions: inner emotion and outer manifestations, spanning static and dynamic, basic and complex, as well as single-modal and cross-modal aspects.<n>A comprehensive evaluation across 22 SOTA video MLLMs reveals notable limitations in current performance, especially in cross-modal and emotion perception.
  arXiv  Detail & Related papers  (2024-12-23T13:45:56Z)
• Multimodal Fusion with LLMs for Engagement Prediction in Natural Conversation [70.52558242336988]
  We focus on predicting engagement in dyadic interactions by scrutinizing verbal and non-verbal cues, aiming to detect signs of disinterest or confusion. In this work, we collect a dataset featuring 34 participants engaged in casual dyadic conversations, each providing self-reported engagement ratings at the end of each conversation. We introduce a novel fusion strategy using Large Language Models (LLMs) to integrate multiple behavior modalities into a multimodal transcript''
  arXiv  Detail & Related papers  (2024-09-13T18:28:12Z)
• MindSpeech: Continuous Imagined Speech Decoding using High-Density fNIRS and Prompt Tuning for Advanced Human-AI Interaction [0.0]
  This paper reports a novel method for human-AI interaction by developing a direct brain-AI interface. We discuss a novel AI model, called MindSpeech, which enables open-vocabulary, continuous decoding for imagined speech. We demonstrate significant improvements in key metrics, such as BLEU-1 and BERT P scores, for three out of four participants.
  arXiv  Detail & Related papers  (2024-07-25T16:39:21Z)
• Social Life Simulation for Non-Cognitive Skills Learning [7.730401608473805]
  We introduce Simulife++, an interactive platform enabled by a large language model (LLM)<n>The system allows users to act as protagonists, creating stories with one or multiple AI-based characters in diverse social scenarios.<n>In particular, we expanded the Human-AI interaction to a Human-AI-AI collaboration by including a Sage Agent, who acts as a bystander.
  arXiv  Detail & Related papers  (2024-05-01T01:45:50Z)
• SoMeLVLM: A Large Vision Language Model for Social Media Processing [78.47310657638567]
  We introduce a Large Vision Language Model for Social Media Processing (SoMeLVLM) SoMeLVLM is a cognitive framework equipped with five key capabilities including knowledge & comprehension, application, analysis, evaluation, and creation. Our experiments demonstrate that SoMeLVLM achieves state-of-the-art performance in multiple social media tasks.
  arXiv  Detail & Related papers  (2024-02-20T14:02:45Z)
• Enabling High-Level Machine Reasoning with Cognitive Neuro-Symbolic Systems [67.01132165581667]
  We propose to enable high-level reasoning in AI systems by integrating cognitive architectures with external neuro-symbolic components. We illustrate a hybrid framework centered on ACT-R and we discuss the role of generative models in recent and future applications.
  arXiv  Detail & Related papers  (2023-11-13T21:20:17Z)
• Building Human-like Communicative Intelligence: A Grounded Perspective [1.0152838128195465]
  After making astounding progress in language learning, AI systems seem to approach the ceiling that does not reflect important aspects of human communicative capacities. This paper suggests that the dominant cognitively-inspired AI directions, based on nativist and symbolic paradigms, lack necessary substantiation and concreteness to guide progress in modern AI. I propose a list of concrete, implementable components for building "grounded" linguistic intelligence.
  arXiv  Detail & Related papers  (2022-01-02T01:43:24Z)
• Human in the Loop for Machine Creativity [0.0]
  We conceptualize existing and future human-in-the-loop (HITL) approaches for creative applications. We examine and speculate on long term implications for models, interfaces, and machine creativity. We envision multimodal HITL processes, where texts, visuals, sounds, and other information are coupled together, with automated analysis of humans and environments.
  arXiv  Detail & Related papers  (2021-10-07T15:42:18Z)
• AEGIS: A real-time multimodal augmented reality computer vision based system to assist facial expression recognition for individuals with autism spectrum disorder [93.0013343535411]
  This paper presents the development of a multimodal augmented reality (AR) system which combines the use of computer vision and deep convolutional neural networks (CNN) The proposed system, which we call AEGIS, is an assistive technology deployable on a variety of user devices including tablets, smartphones, video conference systems, or smartglasses. We leverage both spatial and temporal information in order to provide an accurate expression prediction, which is then converted into its corresponding visualization and drawn on top of the original video frame.
  arXiv  Detail & Related papers  (2020-10-22T17:20:38Z)
• Future Trends for Human-AI Collaboration: A Comprehensive Taxonomy of AI/AGI Using Multiple Intelligences and Learning Styles [95.58955174499371]
  We describe various aspects of multiple human intelligences and learning styles, which may impact on a variety of AI problem domains. Future AI systems will be able not only to communicate with human users and each other, but also to efficiently exchange knowledge and wisdom.
  arXiv  Detail & Related papers  (2020-08-07T21:00:13Z)

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.