# Interlocking-free Selective Rationalization Through Genetic-based Learning

Source: [Interlocking-free Selective Rationalization Through Genetic-based Learning](<https://www.sota2.com/research/paper/68fa78dc1e209131cea7ad91>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T04:57:28.655Z

Authors: Federico Ruggeri, Gaetano Signorelli

Published: 2024-12-13T17:52:48.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Rationalization on Toy (test)](<https://www.sota2.com/research/sota/rationalization-on-toy-test.md>): Rationalization; Toy (test); HI-F1: 76.02.

- [Rationalization on HateXplain Synthetic Skew (test)](<https://www.sota2.com/research/sota/rationalization-on-hatexplain-synthetic-skew-test.md>): Rationalization; HateXplain Synthetic Skew (test); HI-F1: 0.4281.

- [Rationalization on HateXplain (test)](<https://www.sota2.com/research/sota/rationalization-on-hatexplain-test.md>): Rationalization; HateXplain (test); HI-F1: 42.62.

- [Classification on Toy Synthetic Skew (test)](<https://www.sota2.com/research/sota/classification-on-toy-synthetic-skew-test.md>): Classification; Toy Synthetic Skew (test); F1 Score: 99.46.

- [Classification on HateXplain Synthetic Skew (test)](<https://www.sota2.com/research/sota/classification-on-hatexplain-synthetic-skew-test.md>): Classification; HateXplain Synthetic Skew (test); Clf-F1: 69.89.

- [Classification on Toy (test)](<https://www.sota2.com/research/sota/classification-on-toy-test.md>): Classification; Toy (test); F1 Score: 99.

- [Hate Speech Detection on HateXplain (test)](<https://www.sota2.com/research/sota/hate-speech-detection-on-hatexplain-test.md>): Hate Speech Detection; HateXplain (test); Macro F1 Score: 69.71.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2412.10312>)

[PDF](<https://arxiv.org/pdf/2412.10312.pdf>)

[Implementation](<https://github.com/federicoruggeri/gen-spp>)
