Knowledge Affordances for Hybrid Human-AI Information Seeking
TLDR
This paper introduces 'knowledge affordance' to help humans and AI agents identify optimal information sources in complex hybrid environments.
Key contributions
- Introduces "knowledge affordance" (KA) for systematizing information seeking in human-AI environments.
- Defines KAs as declarative, semantic descriptions of what a knowledge source offers for specific questions.
- Proposes KAs are relational, considering an agent's task, preferences, and situational context.
- Connects affordances, semantic web services, knowledge engineering, and mutual intelligibility.
Why it matters
The paper addresses a critical challenge in modern information ecosystems: efficiently finding the right knowledge source. By introducing knowledge affordances, it offers a novel conceptual framework for more transparent and adaptable human-AI collaboration. This could lead to smarter, more intuitive information-seeking systems.
Original Abstract
As information ecosystems grow more heterogeneous, both humans and artificial agents increasingly face a simple yet unresolved question: when seeking knowledge, whom should we ask, and why? Inspired by how people intuitively "read a room", this paper introduces the concept of knowledge affordance (KA) to systematize how agents identify meaningful opportunities for information seeking in hybrid human-AI environments. Rather than introducing a fully formed framework, we propose KAs as declarative, semantically grounded descriptions of what a knowledge source can offer, for which kinds of questions, and with which contextual properties. Additionally, we suggest that KAs are relational, possibly emerging from the interplay between the agent's task, preferences and situational factors. Our contribution is thus a conceptual proposal that connects different research streams, including affordances, semantic web services, knowledge engineering and querying, and mutual intelligibility. We sketch possible research directions to build KA-aware systems that navigate information spaces with greater transparency, adaptability and shared understanding.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.