Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.21615 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915254639788032 |
|---|---|
| author | Kushwaha, Vikas Ragavan, Sruti Srinivasa Roy, Subhajit |
| author_facet | Kushwaha, Vikas Ragavan, Sruti Srinivasa Roy, Subhajit |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_21615 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Measure Based Generalizable Approach to Understandability Kushwaha, Vikas Ragavan, Sruti Srinivasa Roy, Subhajit Human-Computer Interaction Artificial Intelligence Software Engineering 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. |
| title | A Measure Based Generalizable Approach to Understandability |
| topic | Human-Computer Interaction Artificial Intelligence Software Engineering |
| url | https://arxiv.org/abs/2503.21615 |