Showing cs.CLShow all
2 papers · 1 filter
cs.CL2023
Do Smaller Language Models Answer Contextualised Questions Through Memorisation Or Generalisation?
Tim Hartill, Joshua Bensemann, Michael Witbrock +1
A distinction is often drawn between a model's ability to predict a label for an evaluation sample that is directly memorised from highly similar training samples versus an ability…
cs.CL2022
AbductionRules: Training Transformers to Explain Unexpected Inputs
Nathan Young, Qiming Bao, Joshua Bensemann +1
Transformers have recently been shown to be capable of reliably performing logical reasoning over facts and rules expressed in natural language, but abductive reasoning - inference…