Rationalization

By Daniele De Santis. 2021

Subfields: Natural Language Processing, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

1. Kyle McDonell
2. Laria Reynolds

In Safety, Robustness & Interpretability

1. Kyle McDonell
2. Laria Reynolds

Citations in the corpus

• Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm (2021, background): “When extending reasoning, it is essential to discourage premature verdicts, otherwise all subsequent computation serves only to rationalize the already-chosen verdict without improving the probability of the verdict’s accuracy [27].”