A Measure Based Generalizable Approach to Understandability
This work addresses the challenge of making AI-generated information more understandable and steerable for humans, though it is incremental as it surveys existing efforts and lays groundwork rather than presenting a new method.
The paper tackles the problem of AI agents lacking a detailed notion of understandability for effective human-agent communication, proposing a generalizable, domain-agnostic measure based on cognitive science to improve steerability.
Successful agent-human partnerships require that any agent generated information is understandable to the human, and that the human can easily steer the agent towards a goal. Such effective communication requires the agent to develop a finer-level notion of what is understandable to the human. State-of-the-art agents, including LLMs, lack this detailed notion of understandability because they only capture average human sensibilities from the training data, and therefore afford limited steerability (e.g., requiring non-trivial prompt engineering). In this paper, instead of only relying on data, we argue for developing generalizable, domain-agnostic measures of understandability that can be used as directives for these agents. Existing research on understandability measures is fragmented, we survey various such efforts across domains, and lay a cognitive-science-rooted groundwork for more coherent and domain-agnostic research investigations in future.