Interventional Probing in High Dimensions: An NLI Case Study
Julia Rozanova, Marco Valentino, Lucas Cordeiro, André Freitas
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.- Anthology ID:
- 2023.findings-eacl.188
- Volume:
- Findings of the Association for Computational Linguistics: EACL 2023
- Month:
- May
- Year:
- 2023
- Address:
- Dubrovnik, Croatia
- Editors:
- Andreas Vlachos, Isabelle Augenstein
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2489–2500
- Language:
- URL:
- https://aclanthology.org/2023.findings-eacl.188
- DOI:
- 10.18653/v1/2023.findings-eacl.188
- Cite (ACL):
- Julia Rozanova, Marco Valentino, Lucas Cordeiro, and André Freitas. 2023. Interventional Probing in High Dimensions: An NLI Case Study. In Findings of the Association for Computational Linguistics: EACL 2023, pages 2489–2500, Dubrovnik, Croatia. Association for Computational Linguistics.
- Cite (Informal):
- Interventional Probing in High Dimensions: An NLI Case Study (Rozanova et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2023.findings-eacl.188.pdf