Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2406.09702 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910487153737728 |
|---|---|
| author | Kamei, Ryohei Shiono, Daiki Akama, Reina Suzuki, Jun |
| author_facet | Kamei, Ryohei Shiono, Daiki Akama, Reina Suzuki, Jun |
| contents | With the remarkable development of large language models (LLMs), ensuring the factuality of output has become a challenge. However, having all the contents of the response with given knowledge or facts is not necessarily a good thing in dialogues. This study aimed to achieve both attractiveness and factuality in a dialogue response for which a task was set to predict sentences that do not require factual correctness judgment such as agreeing, or personal opinions/feelings. We created a dataset, dialogue dataset annotated with fact-check-needed label (DDFC), for this task via crowdsourcing, and classification tasks were performed on several models using this dataset. The model with the highest classification accuracy could yield about 88% accurate classification results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_09702 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Detecting Response Generation Not Requiring Factual Judgment Kamei, Ryohei Shiono, Daiki Akama, Reina Suzuki, Jun Computation and Language With the remarkable development of large language models (LLMs), ensuring the factuality of output has become a challenge. However, having all the contents of the response with given knowledge or facts is not necessarily a good thing in dialogues. This study aimed to achieve both attractiveness and factuality in a dialogue response for which a task was set to predict sentences that do not require factual correctness judgment such as agreeing, or personal opinions/feelings. We created a dataset, dialogue dataset annotated with fact-check-needed label (DDFC), for this task via crowdsourcing, and classification tasks were performed on several models using this dataset. The model with the highest classification accuracy could yield about 88% accurate classification results. |
| title | Detecting Response Generation Not Requiring Factual Judgment |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2406.09702 |