Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2307.14117 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913218129035264 |
|---|---|
| author | Pang, Richard Yuanzhe Roller, Stephen Cho, Kyunghyun He, He Weston, Jason |
| author_facet | Pang, Richard Yuanzhe Roller, Stephen Cho, Kyunghyun He, He Weston, Jason |
| contents | We study improving social conversational agents by learning from natural dialogue between users and a deployed model, without extra annotations. To implicitly measure the quality of a machine-generated utterance, we leverage signals like user response length, sentiment and reaction of the future human utterances in the collected dialogue episodes. Our experiments use the publicly released deployment data from BlenderBot (Xu et al., 2023). Human evaluation indicates improvements in our new models over baseline responses; however, we find that some proxy signals can lead to more generations with undesirable properties as well. For example, optimizing for conversation length can lead to more controversial or unfriendly generations compared to the baseline, whereas optimizing for positive sentiment or reaction can decrease these behaviors. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2307_14117 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Leveraging Implicit Feedback from Deployment Data in Dialogue Pang, Richard Yuanzhe Roller, Stephen Cho, Kyunghyun He, He Weston, Jason Computation and Language We study improving social conversational agents by learning from natural dialogue between users and a deployed model, without extra annotations. To implicitly measure the quality of a machine-generated utterance, we leverage signals like user response length, sentiment and reaction of the future human utterances in the collected dialogue episodes. Our experiments use the publicly released deployment data from BlenderBot (Xu et al., 2023). Human evaluation indicates improvements in our new models over baseline responses; however, we find that some proxy signals can lead to more generations with undesirable properties as well. For example, optimizing for conversation length can lead to more controversial or unfriendly generations compared to the baseline, whereas optimizing for positive sentiment or reaction can decrease these behaviors. |
| title | Leveraging Implicit Feedback from Deployment Data in Dialogue |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2307.14117 |