Papers by Pavle Marković
Dial BeInfo for Faithfulness: Improving Factuality of Information-Seeking Dialogue via Behavioural Fine-Tuning (2024.findings-emnlp)
Copied to clipboard
Evgeniia Razumovskaia, Ivan Vulić, Pavle Marković, Tomasz Cichy, Qian Zheng, Tsung-Hsien Wen, Paweł Budzianowski
| Challenge: | Pretrained large language models (LLMs) are prone to hallucinations, that is, they generate incoherent or generic responses to queries. |
| Approach: | They propose a method that applies 'behavioural tuning' on the LLMs to aid information-seeking dialogue by comparing three standard datasets. |
| Outcome: | The proposed method improves accuracy on real-life conversations with real users by allowing the models to perform better on the data. |