Processed metadata corrections (closes #4473)

data/xml/2023.findings.xml

@@ -2518,7 +2518,7 @@
       <author><first>Lucas</first><last>Cordeiro</last><affiliation>University of Manchester</affiliation></author>
       <author><first>André</first><last>Freitas</last><affiliation>University of Manchester</affiliation></author>
       <pages>2489-2500</pages>
-      <abstract>Probing strategies have been shown to detectthe presence of various linguistic features inlarge language models; in particular, seman-tic features intermediate to the “natural logic”fragment of the Natural Language Inferencetask (NLI). In the case of natural logic, the rela-tion between the intermediate features and theentailment label is explicitly known: as such,this provides a ripe setting for interventionalstudies on the NLI models’ representations, al-lowing for stronger causal conjectures and adeeper critical analysis of interventional prob-ing methods. In this work, we carry out newand existing representation-level interventionsto investigate the effect of these semantic fea-tures on NLI classification: we perform am-nesic probing (which removes features as di-rected by learned linear probes) and introducethe mnestic probing variation (which forgetsall dimensions except the probe-selected ones).Furthermore, we delve into the limitations ofthese methods and outline some pitfalls havebeen obscuring the effectivity of interventionalprobing studies.</abstract>
+      <abstract>Probing strategies have been shown to detect the presence of various linguistic features in large language models; in particular, semantic features intermediate to the “natural logic” fragment of the Natural Language Inference task (NLI). In the case of natural logic, the relation between the intermediate features and the entailment label is explicitly known: as such, this provides a ripe setting for <i>interventional</i> studies on the NLI models’ representations, allowing for stronger causal conjectures and a deeper critical analysis of interventional probing methods. In this work, we carry out new and existing representation-level interventions to investigate the effect of these semantic features on NLI classification: we perform <i>amnesic</i> probing (which removes features as directed by learned linear probes) and introduce the <i>mnestic</i> probing variation (which forgets all dimensions <i>except</i> the probe-selected ones). Furthermore, we delve into the limitations of these methods and outline some pitfalls have been obscuring the effectivity of interventional probing studies.</abstract>
       <url hash="9ee97fe8">2023.findings-eacl.188</url>
       <bibkey>rozanova-etal-2023-interventional</bibkey>
       <doi>10.18653/v1/2023.findings-eacl.188</doi>