Detoxifying language model outputs: combining multi-agent debates and reinforcement learning for improved summarization.
Saved in:
| Title: | Detoxifying language model outputs: combining multi-agent debates and reinforcement learning for improved summarization. |
|---|---|
| Authors: | Mohan, G. Bharathi1, g_bharathimohan@ch.amrita.edu, Gayathri, M.2, m_gayathri@ch.amirta.edu, Kumar, R. Prasanna1, r_prasannakumar@ch.amrita.edu |
| Source: | Language Resources & Evaluation; Sep2025, Vol. 59 Issue 3, p2705-2736, 32p |
| Database: | Humanities Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| ISSN: | 1574020X |
|---|---|
| DOI: | 10.1007/s10579-025-09830-7 |
