> For the complete documentation index, see [llms.txt](https://www.mlcompendium.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://www.mlcompendium.com/responsible-ai/intro.md). # Introduction A shipped score can be miscalibrated, opaque, or unfair, and a prompt can be too. After this chapter the reader can point at calibration, explanation, fairness, unlearning, and federated training as the constraints on a model that already exists. The chapter starts with the score itself. [Calibration](/responsible-ai/calibration.md) explains why predicted probabilities need calibration and how to adjust them, from classical methods to neural-net approaches such as temperature scaling. Once the numbers can be trusted, the next question is why the model produced them: [Interpretable & Explainable AI (XAI)](/responsible-ai/interpretable-and-explainable-ai-xai.md) gathers the courses, libraries such as LIME, Anchor, and SHAP, and articles on explaining and interpreting ML models. An explained model can still treat people unequally. [Fairness, Accountability, and Transparency](/responsible-ai/fairness-accountability-and-transparency.md) covers regulation, FAT research, bias, debiasing, fairness tools, and privacy. The same concerns reach language models through their inputs, so [Fairness, Accountability, and Transparency In Prompts](/responsible-ai/fairness-accountability-and-transparency-in-prompts.md) collects papers on debiasing with prompts and on LLM hallucinations. The last two pages are about the data behind the model. [Unlearning](/responsible-ai/unlearning.md) is the challenge of erasing a data point's influence on the input-output mapping of an ML model, and [Federated Learning](/responsible-ai/federated-learning.md) points to a guide on training across centralized and decentralized setups. See also [Developing A Virtual Psychologist With Gen-AI](https://pub.towardsai.net/developing-a-virtual-psychologist-with-gen-ai-f2e87c7d7c28) (October 2024), a walk-through of building a Gen-AI chatbot that offers therapeutic assistance and emotional support, a case where every one of these constraints applies at once. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://www.mlcompendium.com/responsible-ai/intro.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. 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.