Long-term Measurements: Towards a Longitudinal Understanding of Human-AI Interactions

• URL: http://arxiv.org/abs/2608.02491v2
• Date: Wed, 05 Aug 2026 04:54:08 GMT
• Title: Long-term Measurements: Towards a Longitudinal Understanding of Human-AI Interactions
• Abstract summary: We discuss how computational methods in the field of NLP need to be combined with measurements used in social science fields.<n>This ability to model human behavioral shifts as a function of model interactions can facilitate online rather than post-hoc detection of problematic behaviors.
• Score: 7.282012402627575
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Language models have taken on the role of a very new type of technology, by virtue of their "human-ness" and rapid integration into users' daily lives. This combination of features can introduce longitudinal risks---cognitive, developmental and socio-affective changes in humans---that might not surface during a short-term interaction, but can have lasting long-term effects on users. This forms the basis of a critical new mission for NLP: to pivot from static, short-term evaluations of text generations to long-term measurements of behavioral changes, towards a diachronic understanding of human-model interactions. In this work, we draw from measurements used in social science fields that are crucial to understand emergent phenomena in longitudinal data. We discuss how computational methods in the field of NLP need to be combined with such measurements, not only to understand long-term safety risks of human-model interactions, but to help steer model development towards positive rather than negative outcomes for users. This ability to model human behavioral shifts as a function of model interactions can facilitate online rather than post-hoc detection of problematic behaviors, and should be leveraged in alignment frameworks to mitigate long-term risks in users.

Related papers

• Beyond Her: Safety Dynamics in Role-play AI Companions [31.494321104359642]
  We investigate safety dynamics in Role-play AI Companions (RACs) usage through a two-part mixed-methods study.<n>We find that users' internalizing problems, the role personality adopted by the RAC, and risk interaction patterns jointly shape safety dynamics.<n>Our findings highlight the importance of modeling safety as a dynamic process rather than a static property.
  arXiv  Detail & Related papers  (2026-06-27T15:11:35Z)
• Learning Whole-Body Human-Humanoid Interaction from Human-Human Demonstrations [63.80827184637476]
  We introduce D-STAR, a hierarchical policy that disentangles when to act from where to act.<n>We validate our framework through extensive and rigorous simulations.
  arXiv  Detail & Related papers  (2026-01-14T14:37:06Z)
• Interact2Ar: Full-Body Human-Human Interaction Generation via Autoregressive Diffusion Models [80.28579390566298]
  We introduce Interact2Ar, a text-conditioned autoregressive diffusion model for generating full-body, human-human interactions.<n>Hand kinematics are incorporated through dedicated parallel branches, enabling high-fidelity full-body generation.<n>Our model enables a series of downstream applications, including temporal motion composition, real-time adaptation to disturbances, and extension beyond dyadic to multi-person scenarios.
  arXiv  Detail & Related papers  (2025-12-22T18:59:50Z)
• 3D Human-Human Interaction Anomaly Detection [9.82406406771152]
  Human-Human Interaction Anomaly Detection (H2IAD) aims to identify anomalous interactive behaviors within collaborative 3D human actions.<n>IADNet outperforms existing Human-centric AD baselines in H2IAD.
  arXiv  Detail & Related papers  (2025-12-15T17:17:55Z)
• HHI-Assist: A Dataset and Benchmark of Human-Human Interaction in Physical Assistance Scenario [63.77482302352545]
  HHI-Assist is a dataset comprising motion capture clips of human-human interactions in assistive tasks.<n>Our work has the potential to significantly enhance robotic assistance policies.
  arXiv  Detail & Related papers  (2025-09-12T09:38:17Z)
• HUMOF: Human Motion Forecasting in Interactive Social Scenes [29.621970821619424]
  Complex scenes present significant challenges for predicting human behaviour due to the abundance of interaction information.<n>We propose an effective method for human motion forecasting in interactive scenes.<n>Our method achieves state-of-the-art performance across four public datasets.
  arXiv  Detail & Related papers  (2025-06-04T09:21:54Z)
• AntEval: Evaluation of Social Interaction Competencies in LLM-Driven Agents [65.16893197330589]
  Large Language Models (LLMs) have demonstrated their ability to replicate human behaviors across a wide range of scenarios. However, their capability in handling complex, multi-character social interactions has yet to be fully explored. We introduce the Multi-Agent Interaction Evaluation Framework (AntEval), encompassing a novel interaction framework and evaluation methods.
  arXiv  Detail & Related papers  (2024-01-12T11:18:00Z)
• IA-LSTM: Interaction-Aware LSTM for Pedestrian Trajectory Prediction [1.3597551064547502]
  Predicting the trajectory of pedestrians in crowd scenarios is indispensable in self-driving or autonomous mobile robot field. Previous researchers focused on how to model human-human interactions but neglected the relative importance of interactions. New mechanism based on correntropy is introduced to measure the relative importance of human-human interactions.
  arXiv  Detail & Related papers  (2023-11-26T05:17:11Z)
• Comparison of Spatio-Temporal Models for Human Motion and Pose Forecasting in Face-to-Face Interaction Scenarios [47.99589136455976]
  We present the first systematic comparison of state-of-the-art approaches for behavior forecasting. Our best attention-based approaches achieve state-of-the-art performance in UDIVA v0.5. We show that by autoregressively predicting the future with methods trained for the short-term future, we outperform the baselines even for a considerably longer-term future.
  arXiv  Detail & Related papers  (2022-03-07T09:59:30Z)
• User profile-driven large-scale multi-agent learning from demonstration in federated human-robot collaborative environments [5.218882272051637]
  This paper introduces a novel user profile formulation for providing a fine-grained representation of the exhibited human behavior. The overall designed scheme enables both short- and long-term analysis/interpretation of the human behavior.
  arXiv  Detail & Related papers  (2021-03-30T15:33:21Z)
• Human Trajectory Forecasting in Crowds: A Deep Learning Perspective [89.4600982169]
  We present an in-depth analysis of existing deep learning-based methods for modelling social interactions. We propose two knowledge-based data-driven methods to effectively capture these social interactions. We develop a large scale interaction-centric benchmark TrajNet++, a significant yet missing component in the field of human trajectory forecasting.
  arXiv  Detail & Related papers  (2020-07-07T17:19:56Z)

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.