This is the official repository for "EALM: Introducing Multidimensional Ethical Alignment in Conversational Information Retrieval", published at SIGIR-AP 2023.
The MP-ETHICS dataset is uploaded.
| Method | Samples F1 score (%) |
|---|---|
| EALM (ours) | 44.5 |
| DeBERTa3-large | 38.1 |
| DeBERTa-base | 37.3 |
| RoBERTa-base | 35.7 |
Current results present the MP-ETHICS leaderboard showcasing the performance comparison of various methods.