# Ethics

This domain is intended to codify ethics-related, often unintentional failure modes, e.g. algorithmic bias, misinformation.

<table><thead><tr><th width="97">ID</th><th width="90">Sub-ID</th><th>Name</th><th>Description</th></tr></thead><tbody><tr><td>E0100</td><td></td><td>Bias/Discrimination</td><td>Concerns of algorithms propagating societal bias</td></tr><tr><td></td><td>E0101</td><td>Group fairness</td><td>Fairness towards specific groups of people</td></tr><tr><td></td><td>E0102</td><td>Individual fairness</td><td>Fairness in treating similar individuals</td></tr><tr><td>E0200</td><td></td><td>Explainability</td><td>Ability to explain decisions made by AI</td></tr><tr><td></td><td>E0201</td><td>Global explanations</td><td>Explain overall functionality</td></tr><tr><td></td><td>E0202</td><td>Local explanations</td><td>Explain specific decisions</td></tr><tr><td>E0300</td><td></td><td>User actions</td><td>Perpetuating/causing/being affected by negative user actions</td></tr><tr><td></td><td>E0301</td><td>Toxicity</td><td>Users hostile towards other users</td></tr><tr><td></td><td>E0302</td><td>Polarization/ Exclusion</td><td>User behavior skewed in a significant direction</td></tr><tr><td>E0400</td><td></td><td>Misinformation</td><td>Perpetuating/causing the spread of falsehoods</td></tr><tr><td></td><td>E0401</td><td>Deliberative Misinformation</td><td>Generated by individuals., e.g. vaccine disinformation</td></tr><tr><td></td><td>E0402</td><td>Generative Misinformation</td><td>Generated algorithmically, e.g. Deep Fakes</td></tr></tbody></table>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.avidml.org/taxonomy/effect-sep-view/ethics.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.