Counting Worlds Branching Time Semantics for post-hoc Bias Mitigation in generative AI
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911611880472576 |
|---|---|
| author | Buda, Alessandro G. Primiero, Giuseppe Ceragioli, Leonardo Antonelli, Melissa |
| author_facet | Buda, Alessandro G. Primiero, Giuseppe Ceragioli, Leonardo Antonelli, Melissa |
| contents | Generative AI systems are known to amplify biases present in their training data. While several inference-time mitigation strategies have been proposed, they remain largely empirical and lack formal guarantees. In this paper we introduce CTLF, a branching-time logic designed to reason about bias in series of generative AI outputs. CTLF adopts a counting worlds semantics where each world represents a possible output at a given step in the generation process and introduces modal operators that allow us to verify whether the current output series respects an intended probability distribution over a protected attribute, to predict the likelihood of remaining within acceptable bounds as new outputs are generated, and to determine how many outputs are needed to remove in order to restore fairness. We illustrate the framework on a toy example of biased image generation, showing how CTLF formulas can express concrete fairness properties at different points in the output series. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_19431 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Counting Worlds Branching Time Semantics for post-hoc Bias Mitigation in generative AI Buda, Alessandro G. Primiero, Giuseppe Ceragioli, Leonardo Antonelli, Melissa Logic in Computer Science Artificial Intelligence Generative AI systems are known to amplify biases present in their training data. While several inference-time mitigation strategies have been proposed, they remain largely empirical and lack formal guarantees. In this paper we introduce CTLF, a branching-time logic designed to reason about bias in series of generative AI outputs. CTLF adopts a counting worlds semantics where each world represents a possible output at a given step in the generation process and introduces modal operators that allow us to verify whether the current output series respects an intended probability distribution over a protected attribute, to predict the likelihood of remaining within acceptable bounds as new outputs are generated, and to determine how many outputs are needed to remove in order to restore fairness. We illustrate the framework on a toy example of biased image generation, showing how CTLF formulas can express concrete fairness properties at different points in the output series. |
| title | Counting Worlds Branching Time Semantics for post-hoc Bias Mitigation in generative AI |
| topic | Logic in Computer Science Artificial Intelligence |
| url | https://arxiv.org/abs/2604.19431 |