Papers by Heidi Zhang
SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic Parsing (2024.findings-acl)
Copied to clipboard
| Challenge: | SPAGHETTI: Semantic Parsing Augmented Generation for Hybrid English information from Text Tables and Infoboxes is a hybrid question-answering pipeline . |
| Approach: | They propose a hybrid question-answering pipeline that leverages knowledge from multiple knowledge sources. |
| Outcome: | The proposed approach achieves state-of-the-art on the Compmix dataset with 56.5% exact match rate. |
WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia (2023.findings-emnlp)
Copied to clipboard
| Challenge: | a new few-shot LLM-based chatbot is able to provide factual and engaging responses . a novel hybrid human-and-LLM evaluation methodology is used to evaluate the system . |
| Approach: | They propose a few-shot LLM-based chatbot that almost never hallucinates . they distill WikiChat into a 7B-parameter LLaMA model with minimal loss of quality . |
| Outcome: | The proposed system outperforms retrieval-based and LLM-based systems on the Wikipedia corpus. |