The Effect of Model Size on LLM Post-hoc Explainability via LIME
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916239448735744 |
|---|---|
| author | Heyen, Henning Widdicombe, Amy Siegel, Noah Y. Perez-Ortiz, Maria Treleaven, Philip |
| author_facet | Heyen, Henning Widdicombe, Amy Siegel, Noah Y. Perez-Ortiz, Maria Treleaven, Philip |
| contents | Large language models (LLMs) are becoming bigger to boost performance. However, little is known about how explainability is affected by this trend. This work explores LIME explanations for DeBERTaV3 models of four different sizes on natural language inference (NLI) and zero-shot classification (ZSC) tasks. We evaluate the explanations based on their faithfulness to the models' internal decision processes and their plausibility, i.e. their agreement with human explanations. The key finding is that increased model size does not correlate with plausibility despite improved model performance, suggesting a misalignment between the LIME explanations and the models' internal processes as model size increases. Our results further suggest limitations regarding faithfulness metrics in NLI contexts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_05348 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | The Effect of Model Size on LLM Post-hoc Explainability via LIME Heyen, Henning Widdicombe, Amy Siegel, Noah Y. Perez-Ortiz, Maria Treleaven, Philip Computation and Language Artificial Intelligence Machine Learning Large language models (LLMs) are becoming bigger to boost performance. However, little is known about how explainability is affected by this trend. This work explores LIME explanations for DeBERTaV3 models of four different sizes on natural language inference (NLI) and zero-shot classification (ZSC) tasks. We evaluate the explanations based on their faithfulness to the models' internal decision processes and their plausibility, i.e. their agreement with human explanations. The key finding is that increased model size does not correlate with plausibility despite improved model performance, suggesting a misalignment between the LIME explanations and the models' internal processes as model size increases. Our results further suggest limitations regarding faithfulness metrics in NLI contexts. |
| title | The Effect of Model Size on LLM Post-hoc Explainability via LIME |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2405.05348 |