Saved in:
Bibliographic Details
Main Authors: Liu, Zihan, Rabbani, Parisa, Duddu, Veda, Fan, Kyle, Lee, Madison, Huang, Yun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.23947
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908661517910016
author Liu, Zihan
Rabbani, Parisa
Duddu, Veda
Fan, Kyle
Lee, Madison
Huang, Yun
author_facet Liu, Zihan
Rabbani, Parisa
Duddu, Veda
Fan, Kyle
Lee, Madison
Huang, Yun
contents LLM-powered multimodal systems are increasingly used to interpret human behavior, yet how researchers apply the models' 'social competence' remains poorly understood. This paper presents a systematic literature review of 176 publications across different application domains (e.g., healthcare, education, and entertainment). Using a four-dimensional coding framework (application, technical, evaluative, and ethical), we find (1) frequent use of pattern recognition and information extraction from multimodal sources, but limited support for adaptive, interactive reasoning; (2) a dominant 'modality-to-text' pipeline that privileges language over rich audiovisual cues, striping away nuanced social cues; (3) evaluation practices reliant on static benchmarks, with socially grounded, human-centered assessments rare; and (4) Ethical discussions focused mainly on legal and rights-related risks (e.g., privacy), leaving societal risks (e.g., deception) overlooked--or at best acknowledged but left unaddressed. We outline a research agenda for evaluating socially competent, ethically informed, and interaction-aware multi-modal systems.
format Preprint
id arxiv_https___arxiv_org_abs_2510_23947
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Social Gaze of LLMs: A Literature Review of Multimodal Approaches to Human Behavior Understanding
Liu, Zihan
Rabbani, Parisa
Duddu, Veda
Fan, Kyle
Lee, Madison
Huang, Yun
Human-Computer Interaction
LLM-powered multimodal systems are increasingly used to interpret human behavior, yet how researchers apply the models' 'social competence' remains poorly understood. This paper presents a systematic literature review of 176 publications across different application domains (e.g., healthcare, education, and entertainment). Using a four-dimensional coding framework (application, technical, evaluative, and ethical), we find (1) frequent use of pattern recognition and information extraction from multimodal sources, but limited support for adaptive, interactive reasoning; (2) a dominant 'modality-to-text' pipeline that privileges language over rich audiovisual cues, striping away nuanced social cues; (3) evaluation practices reliant on static benchmarks, with socially grounded, human-centered assessments rare; and (4) Ethical discussions focused mainly on legal and rights-related risks (e.g., privacy), leaving societal risks (e.g., deception) overlooked--or at best acknowledged but left unaddressed. We outline a research agenda for evaluating socially competent, ethically informed, and interaction-aware multi-modal systems.
title The Social Gaze of LLMs: A Literature Review of Multimodal Approaches to Human Behavior Understanding
topic Human-Computer Interaction
url https://arxiv.org/abs/2510.23947