Papers by Muhammad AL-Qurishi
Improving LLM Domain Certification with Pretrained Guide Models (2026.eacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) generate off-domain or harmful responses when deployed in high-stakes domains. |
| Approach: | They propose a method that leverages pretrained language models as guide models to sharply distinguish acceptable from refused content. |
| Outcome: | The proposed approach exploits pretrained language models as guide models while aligned to the target domain. |