相关论文: HCC Is All You Need: Alignment-The Sensible Kind A…

In many practical applications of AI, an AI model is used as a decision aid for human users. The AI provides advice that a human (sometimes) incorporates into their decision-making process. The AI advice is often presented with some measure…

Human parsing is for pixel-wise human semantic understanding. As human bodies are underlying hierarchically structured, how to model human structures is the central theme in this task. Focusing on this, we seek to simultaneously exploit the…

Grounding is a challenging problem, requiring a formal definition and different levels of abstraction. This article explores grounding from both cognitive science and machine learning perspectives. It identifies the subtleties of grounding,…

Human Computer Symbiosis is similar to Human Computer Interaction in the sense that it is about how humans and computer interact with each other. For this interaction to be made there needs to be a symbiotic relationship between man and…

Recent progress in artificial intelligence (AI) has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video…

Data-centric artificial intelligence (data-centric AI) represents an emerging paradigm emphasizing that the systematic design and engineering of data is essential for building effective and efficient AI-based systems. The objective of this…

Given that Artificial Intelligence (AI) increasingly permeates our lives, it is critical that we systematically align AI objectives with the goals and values of humans. The human-AI alignment problem stems from the impracticality of…

Supervised Learning is a way of developing Artificial Intelligence systems in which a computer algorithm is trained on labeled data inputs. Effectiveness of a Supervised Learning algorithm is determined by its performance on a given dataset…

Existing work on the alignment problem has focused mainly on (1) qualitative descriptions of the alignment problem; (2) attempting to align AI actions with human interests by focusing on value specification and learning; and/or (3) focusing…

In AI-assisted decision-making, it is critical for human decision-makers to know when to trust AI and when to trust themselves. However, prior studies calibrated human trust only based on AI confidence indicating AI's correctness likelihood…

Machine common sense remains a broad, potentially unbounded problem in artificial intelligence (AI). There is a wide range of strategies that can be employed to make progress on this challenge. This article deals with the aspects of…

Modern machine learning models typically represent inputs as fixed points in a high-dimensional embedding space. While this approach has been proven powerful for a wide range of downstream tasks, it fundamentally differs from the way humans…

Reasoning is a distinctive human-like characteristic attributed to LLMs in HCI due to their ability to simulate various human-level tasks. However, this work argues that the reasoning behavior of LLMs in HCI is often decontextualized from…

This paper introduces function alignment, a novel theory of mind and intelligence that is both intuitively compelling and structurally grounded. It explicitly models how meaning, interpretation, and analogy emerge from interactions among…

While XAI focuses on providing AI explanations to humans, can the reverse - humans explaining their judgments to AI - foster richer, synergistic human-AI systems? This paper explores various forms of human inputs to AI and examines how…

AI alignment is often framed as the task of ensuring that an AI system follows a set of stated principles or human preferences, but general principles rarely determine their own application in concrete cases. When principles conflict, when…

Despite its technological breakthroughs, eXplainable Artificial Intelligence (XAI) research has limited success in producing the {\em effective explanations} needed by users. In order to improve XAI systems' usability, practical…

Human-centered artificial intelligence (HCAI) is an approach to AI design, development, and deployment that prioritizes human needs, values, and experiences, ensuring that technology enhances human capabilities, well-being, and workforce…

Through systematically analyzing the literature on designing AI-based technologies, we extracted design implications and synthesized them into a generic human-centered design framework for AI technologies to better support human needs and…

In this paper, I put forward that in many instances, thinking mechanisms are equivalent to artificial intelligence modules programmed into the human mind.