Works · Framework Demo
LLMs can overreact to subtle demographic cues in implicit hate speech. FairToT is the first framework to ask when fairness correction should be invoked at inference time: it substitutes demographic entities into a sentence, measures how much the model's toxicity judgement swings, and only applies prompt-guided correction when that swing signals real instability — without retraining the model.
How it works
The sentence is scored for toxicity once, unmodified (ENR baseline).
The named demographic entity is swapped across groups and re-scored each time.
Sentence Fairness Variance and Entity Fairness Dispersion quantify how much scores swing across groups.
Only when variance exceeds threshold is prompt-guided correction applied — stable cases pass through untouched.
Worked example
Illustrative scores in the shape of the paper's metrics — not a live model call. Demographic groups are anonymized as Group A/B/C to keep this example abstract.
—