Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answering
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912029897392128 |
|---|---|
| author | Shi, Zhengliang Sun, Weiwei Gao, Shen Ren, Pengjie Chen, Zhumin Ren, Zhaochun |
| author_facet | Shi, Zhengliang Sun, Weiwei Gao, Shen Ren, Pengjie Chen, Zhumin Ren, Zhaochun |
| contents | Multi-Hop Question Answering (MHQA) tasks present a significant challenge for large language models (LLMs) due to the intensive knowledge required. Current solutions, like Retrieval-Augmented Generation, typically retrieve potential documents from an external corpus to read an answer. However, the performance of this retrieve-then-read paradigm is constrained by the retriever and the inevitable noise in the retrieved documents. To mitigate these challenges, we introduce a novel generate-then-ground (GenGround) framework, synergizing the parametric knowledge of LLMs and external documents to solve a multi-hop question. GenGround empowers LLMs to alternate two phases until the final answer is derived: (1) formulate a simpler, single-hop question and directly generate the answer; (2) ground the question-answer pair in retrieved documents, amending any wrong predictions in the answer. We also propose an instructional grounding distillation method to generalize our method into smaller models. Extensive experiments conducted on four datasets illustrate the superiority of our method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_14891 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answering Shi, Zhengliang Sun, Weiwei Gao, Shen Ren, Pengjie Chen, Zhumin Ren, Zhaochun Computation and Language Information Retrieval Multi-Hop Question Answering (MHQA) tasks present a significant challenge for large language models (LLMs) due to the intensive knowledge required. Current solutions, like Retrieval-Augmented Generation, typically retrieve potential documents from an external corpus to read an answer. However, the performance of this retrieve-then-read paradigm is constrained by the retriever and the inevitable noise in the retrieved documents. To mitigate these challenges, we introduce a novel generate-then-ground (GenGround) framework, synergizing the parametric knowledge of LLMs and external documents to solve a multi-hop question. GenGround empowers LLMs to alternate two phases until the final answer is derived: (1) formulate a simpler, single-hop question and directly generate the answer; (2) ground the question-answer pair in retrieved documents, amending any wrong predictions in the answer. We also propose an instructional grounding distillation method to generalize our method into smaller models. Extensive experiments conducted on four datasets illustrate the superiority of our method. |
| title | Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answering |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2406.14891 |