Interlocking-free Selective Rationalization Through Genetic-based Learning
Year: 2025
Type: conference-paper
Abstract: A popular end-to-end architecture for selective rationalization is the select-then-predict pipeline, comprising a generator to extract highlights fed to a predictor. Such a cooperative system suffers from suboptimal equilibrium minima due to the dominance of one of the two modules, a phenomenon known as interlocking. While several contributions aimed at addressing interlocking, they only mitigate its effect, often by introducing feature-based heuristics, sampling, and ad-hoc regularizations. We present GenSPP, the first interlocking-free architecture for selective rationalization that does not require any learning overhead, as the above-mentioned. GenSPP avoids interlocking by performing disjoint training of the generator and predictor via genetic global search. Experiments on a synthetic and a real-world benchmark show that our model outperforms several state-of-the-art competitors.
Authors: Federico Ruggeri, Gaetano Signorelli
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Funders: European Commission, Justice Programme
Award: G4508289328
OpenAlex ID: W4412886832