Conceptual Contrastive Edits in Textual and Vision-Language Retrieval
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915181235273728 |
|---|---|
| author | Lymperaiou, Maria Stamou, Giorgos |
| author_facet | Lymperaiou, Maria Stamou, Giorgos |
| contents | As deep learning models grow in complexity, achieving model-agnostic interpretability becomes increasingly vital. In this work, we employ post-hoc conceptual contrastive edits to expose noteworthy patterns and biases imprinted in representations of retrieval models. We systematically design optimal and controllable contrastive interventions targeting various parts of speech, and effectively apply them to explain both linguistic and visiolinguistic pre-trained models in a black-box manner. Additionally, we introduce a novel metric to assess the per-word impact of contrastive interventions on model outcomes, providing a comprehensive evaluation of each intervention's effectiveness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_01914 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Conceptual Contrastive Edits in Textual and Vision-Language Retrieval Lymperaiou, Maria Stamou, Giorgos Computation and Language Artificial Intelligence As deep learning models grow in complexity, achieving model-agnostic interpretability becomes increasingly vital. In this work, we employ post-hoc conceptual contrastive edits to expose noteworthy patterns and biases imprinted in representations of retrieval models. We systematically design optimal and controllable contrastive interventions targeting various parts of speech, and effectively apply them to explain both linguistic and visiolinguistic pre-trained models in a black-box manner. Additionally, we introduce a novel metric to assess the per-word impact of contrastive interventions on model outcomes, providing a comprehensive evaluation of each intervention's effectiveness. |
| title | Conceptual Contrastive Edits in Textual and Vision-Language Retrieval |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2503.01914 |