Human intention-based systems enable robots to perceive and interpret user actions to interact with humans and adapt to their behavior proactively. Therefore, intention prediction is pivotal in creating a natural interaction with social robots in human-designed environments. In this paper, we examine using Large Language Models (LLMs) to infer human intention in a collaborative object categorization task with a physical robot. We propose a novel multimodal approach that integrates user non-verbal cues, like hand gestures, body poses, and facial expressions, with environment states and user verbal cues to predict user intentions in a hierarchical architecture. Our evaluation of five LLMs shows the potential for reasoning about verbal and non-verbal user cues, leveraging their context-understanding and real-world knowledge to support intention prediction while collaborating on a task with a social robot.
相關內容
The research community has traditionally shown a keen interest in emotion modeling, with a notable emphasis on the detection aspect. In contrast, the exploration of emotion generation has received less attention.This study delves into an existing state-of-the-art emotional chatbot, EmoBot, designed for generating emotions in general-purpose conversations. This research involves a comprehensive examination, including a survey to evaluate EmoBot's proficiency in key dimensions like usability, accuracy, and overall user satisfaction, with a specific focus on fault tolerance. By closely examining the chatbot's operations, we identified some noteworthy shortcomings in the existing model. We propose some solutions designed to address and overcome the identified issues.
Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer
Aligning generative models with human preference via RLHF typically suffers from overoptimization, where an imperfectly learned reward model can misguide the generative model to output undesired responses. We investigate this problem in a principled manner by identifying the source of the misalignment as a form of distributional shift and uncertainty in learning human preferences. To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model; one that simultaneously minimizes the maximum likelihood estimation of the loss and a reward penalty term. Here, the reward penalty term is introduced to prevent the policy from choosing actions with spurious high proxy rewards, resulting in provable sample efficiency of the algorithm under a partial coverage style condition. Moving from theory to practice, the proposed algorithm further enjoys an equivalent but surprisingly easy-to-implement reformulation. Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines: (i) a preference optimization loss that directly aligns the policy with human preference, and (ii) a supervised learning loss that explicitly imitates the policy with a (suitable) baseline distribution. In the context of aligning large language models (LLM), this objective fuses the direct preference optimization (DPO) loss with the supervised fine-tuning (SFT) loss to help mitigate the overoptimization towards undesired responses, for which we name the algorithm Regularized Preference Optimization (RPO). Experiments of aligning LLMs demonstrate the improved performance of RPO compared with DPO baselines. Our work sheds light on the interplay between preference optimization and SFT in tuning LLMs with both theoretical guarantees and empirical evidence.
Existing gesture interfaces only work with a fixed set of gestures defined either by interface designers or by users themselves, which introduces learning or demonstration efforts that diminish their naturalness. Humans, on the other hand, understand free-form gestures by synthesizing the gesture, context, experience, and common sense. In this way, the user does not need to learn, demonstrate, or associate gestures. We introduce GestureGPT, a free-form hand gesture understanding framework that mimics human gesture understanding procedures to enable a natural free-form gestural interface. Our framework leverages multiple Large Language Model agents to manage and synthesize gesture and context information, then infers the interaction intent by associating the gesture with an interface function. More specifically, our triple-agent framework includes a Gesture Description Agent that automatically segments and formulates natural language descriptions of hand poses and movements based on hand landmark coordinates. The description is deciphered by a Gesture Inference Agent through self-reasoning and querying about the interaction context (e.g., interaction history, gaze data), which is managed by a Context Management Agent. Following iterative exchanges, the Gesture Inference Agent discerns the user's intent by grounding it to an interactive function. We validated our framework offline under two real-world scenarios: smart home control and online video streaming. The average zero-shot Top-1/Top-5 grounding accuracies are 44.79%/83.59% for smart home tasks and 37.50%/73.44% for video streaming tasks. We also provide an extensive discussion that includes rationale for model selection, generalizability, and future research directions for a practical system etc.
As human-agent teaming (HAT) research continues to grow, computational methods for modeling HAT behaviors and measuring HAT effectiveness also continue to develop. One rising method involves the use of human digital twins (HDT) to approximate human behaviors and socio-emotional-cognitive reactions to AI-driven agent team members. In this paper, we address three research questions relating to the use of digital twins for modeling trust in HATs. First, to address the question of how we can appropriately model and operationalize HAT trust through HDT HAT experiments, we conducted causal analytics of team communication data to understand the impact of empathy, socio-cognitive, and emotional constructs on trust formation. Additionally, we reflect on the current state of the HAT trust science to discuss characteristics of HAT trust that must be replicable by a HDT such as individual differences in trust tendencies, emergent trust patterns, and appropriate measurement of these characteristics over time. Second, to address the question of how valid measures of HDT trust are for approximating human trust in HATs, we discuss the properties of HDT trust: self-report measures, interaction-based measures, and compliance type behavioral measures. Additionally, we share results of preliminary simulations comparing different LLM models for generating HDT communications and analyze their ability to replicate human-like trust dynamics. Third, to address how HAT experimental manipulations will extend to human digital twin studies, we share experimental design focusing on propensity to trust for HDTs vs. transparency and competency-based trust for AI agents.
Communication traits in text-based human-AI conversations play pivotal roles in shaping user experiences and perceptions of systems. With the advancement of large language models (LLMs), it is now feasible to analyze these traits at a more granular level. In this study, we explore the preferences of information workers regarding chatbot communication traits across seven applications. Participants were invited to participate in an interactive survey, which featured adjustable sliders, allowing them to adjust and express their preferences for five key communication traits: formality, personification, empathy, sociability, and humor. Our findings reveal distinct communication preferences across different applications; for instance, there was a preference for relatively high empathy in wellbeing contexts and relatively low personification in coding. Similarities in preferences were also noted between applications such as chatbots for customer service and scheduling. These insights offer crucial design guidelines for future chatbots, emphasizing the need for nuanced trait adjustments for each application.
Tapping buttons and hyperlinks on smartphones is a fundamental operation, but users sometimes fail to tap user-interface (UI) elements. Such mistakes degrade usability, and thus it is important for designers to configure UI elements so that users can accurately select them. To support designers in setting a UI element with an intended tap success rate, we developed a plugin for Figma, which is modern software for developing webpages and applications for smartphones, based on our previously launched web-based application, Tappy. This plugin converts the size of a UI element from pixels to mm and then computes the tap success rates based on the Dual Gaussian Distribution Model. We have made this plugin freely available to external users, so readers can install the Tappy plugin for Figma by visiting its installation page (//www.figma.com/community/plugin/66437139/tappy) or from their desktop Figma software.
Sequential recommendation systems predict the next interaction item based on users' past interactions, aligning recommendations with individual preferences. Leveraging the strengths of Large Language Models (LLMs) in knowledge comprehension and reasoning, recent approaches are eager to apply LLMs to sequential recommendation. A common paradigm is converting user behavior sequences into instruction data, and fine-tuning the LLM with parameter-efficient fine-tuning (PEFT) methods like Low-Rank Adaption (LoRA). However, the uniform application of LoRA across diverse user behaviors is insufficient to capture individual variability, resulting in negative transfer between disparate sequences. To address these challenges, we propose Instance-wise LoRA (iLoRA). We innovatively treat the sequential recommendation task as a form of multi-task learning, integrating LoRA with the Mixture of Experts (MoE) framework. This approach encourages different experts to capture various aspects of user behavior. Additionally, we introduce a sequence representation guided gate function that generates customized expert participation weights for each user sequence, which allows dynamic parameter adjustment for instance-wise recommendations. In sequential recommendation, iLoRA achieves an average relative improvement of 11.4\% over basic LoRA in the hit ratio metric, with less than a 1\% relative increase in trainable parameters. Extensive experiments on three benchmark datasets demonstrate the effectiveness of iLoRA, highlighting its superior performance compared to existing methods in mitigating negative transfer and improving recommendation accuracy. Our data and code are available at //github.com/AkaliKong/iLoRA.
Sequential recommender systems (SRS) aim to predict users' subsequent choices based on their historical interactions and have found applications in diverse fields such as e-commerce and social media. However, in real-world systems, most users interact with only a handful of items, while the majority of items are seldom consumed. These two issues, known as the long-tail user and long-tail item challenges, often pose difficulties for existing SRS. These challenges can adversely affect user experience and seller benefits, making them crucial to address. Though a few works have addressed the challenges, they still struggle with the seesaw or noisy issues due to the intrinsic scarcity of interactions. The advancements in large language models (LLMs) present a promising solution to these problems from a semantic perspective. As one of the pioneers in this field, we propose the Large Language Models Enhancement framework for Sequential Recommendation (LLM-ESR). This framework utilizes semantic embeddings derived from LLMs to enhance SRS without adding extra inference load from LLMs. To address the long-tail item challenge, we design a dual-view modeling framework that combines semantics from LLMs and collaborative signals from conventional SRS. For the long-tail user challenge, we propose a retrieval augmented self-distillation method to enhance user preference representation using more informative interactions from similar users. To verify the effectiveness and versatility of our proposed enhancement framework, we conduct extensive experiments on three real-world datasets using three popular SRS models. The results show that our method surpasses existing baselines consistently, and benefits long-tail users and items especially. The implementation code is available at //github.com/Applied-Machine-Learning-Lab/LLM-ESR.
Existing recommender systems extract the user preference based on learning the correlation in data, such as behavioral correlation in collaborative filtering, feature-feature, or feature-behavior correlation in click-through rate prediction. However, regretfully, the real world is driven by causality rather than correlation, and correlation does not imply causation. For example, the recommender systems can recommend a battery charger to a user after buying a phone, in which the latter can serve as the cause of the former, and such a causal relation cannot be reversed. Recently, to address it, researchers in recommender systems have begun to utilize causal inference to extract causality, enhancing the recommender system. In this survey, we comprehensively review the literature on causal inference-based recommendation. At first, we present the fundamental concepts of both recommendation and causal inference as the basis of later content. We raise the typical issues that the non-causality recommendation is faced. Afterward, we comprehensively review the existing work of causal inference-based recommendation, based on a taxonomy of what kind of problem causal inference addresses. Last, we discuss the open problems in this important research area, along with interesting future works.
Autonomic computing investigates how systems can achieve (user) specified control outcomes on their own, without the intervention of a human operator. Autonomic computing fundamentals have been substantially influenced by those of control theory for closed and open-loop systems. In practice, complex systems may exhibit a number of concurrent and inter-dependent control loops. Despite research into autonomic models for managing computer resources, ranging from individual resources (e.g., web servers) to a resource ensemble (e.g., multiple resources within a data center), research into integrating Artificial Intelligence (AI) and Machine Learning (ML) to improve resource autonomy and performance at scale continues to be a fundamental challenge. The integration of AI/ML to achieve such autonomic and self-management of systems can be achieved at different levels of granularity, from full to human-in-the-loop automation. In this article, leading academics, researchers, practitioners, engineers, and scientists in the fields of cloud computing, AI/ML, and quantum computing join to discuss current research and potential future directions for these fields. Further, we discuss challenges and opportunities for leveraging AI and ML in next generation computing for emerging computing paradigms, including cloud, fog, edge, serverless and quantum computing environments.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191