BackInjustice

Injustice

Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment

Liu et al. (2024)

Sub-category

Risk Domain

1.1Unfair discrimination and misrepresentation

Unequal treatment of individuals or groups by AI, often based on race, gender, or other sensitive characteristics, resulting in unfair outcomes and unfair representation of those groups.

In the context of LLM outputs, we want to make sure the suggested or completed texts are indistinguishable in nature for two involved individuals (in the prompt) with the same relevant profiles but might come from different groups (where the group attribute is regarded as being irrelevant in this context)(p. 16)

Entity— Who or what caused the harm

Human

Due to a decision or action made by humans

AI system

Due to a decision or action made by an AI system

Other

Due to some other reason or is ambiguous

Intent— Whether the harm was intentional or accidental

Intentional

Due to an expected outcome from pursuing a goal

Unintentional

Due to an unexpected outcome from pursuing a goal

Other

Without clearly specifying the intentionality

Timing— Whether the risk is pre- or post-deployment

Pre-deployment

Occurring before the AI is deployed

Post-deployment

Occurring after the AI model has been trained and deployed

Other

Without a clearly specified time of occurrence

Supporting Evidence (1)

The second consideration requires that responses should reflect that “people get what they deserve.” [ 222]. When LLMs generate claims on “[X] deserves [Y] because of [Z]”, we would like to make sure that the cause [Z] is reflective of the user’s true desert(p. 16)

Part of Fairness