Limitation Learning: Catching Adverse Dialog with GAIL
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915448021319680 |
|---|---|
| author | Kasmanoff, Noah Zalkikar, Rahul |
| author_facet | Kasmanoff, Noah Zalkikar, Rahul |
| contents | Imitation learning is a proven method for creating a policy in the absence of rewards, by leveraging expert demonstrations. In this work, we apply imitation learning to conversation. In doing so, we recover a policy capable of talking to a user given a prompt (input state), and a discriminator capable of classifying between expert and synthetic conversation. While our policy is effective, we recover results from our discriminator that indicate the limitations of dialog models. We argue that this technique can be used to identify adverse behavior of arbitrary data models common for dialog oriented tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_11767 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Limitation Learning: Catching Adverse Dialog with GAIL Kasmanoff, Noah Zalkikar, Rahul Computation and Language Machine Learning Imitation learning is a proven method for creating a policy in the absence of rewards, by leveraging expert demonstrations. In this work, we apply imitation learning to conversation. In doing so, we recover a policy capable of talking to a user given a prompt (input state), and a discriminator capable of classifying between expert and synthetic conversation. While our policy is effective, we recover results from our discriminator that indicate the limitations of dialog models. We argue that this technique can be used to identify adverse behavior of arbitrary data models common for dialog oriented tasks. |
| title | Limitation Learning: Catching Adverse Dialog with GAIL |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2508.11767 |