Zhenkai Wei
2024
Retrieving, Rethinking and Revising: The Chain-of-Verification Can Improve Retrieval Augmented Generation
Bolei He
|
Nuo Chen
|
Xinran He
|
Lingyong Yan
|
Zhenkai Wei
|
Jinchang Luo
|
Zhen-Hua Ling
Findings of the Association for Computational Linguistics: EMNLP 2024
Recent Retrieval Augmented Generation (RAG) aims to enhance Large Language Models (LLMs) by incorporating extensive knowledge retrieved from external sources. However, such approach encounters some challenges: Firstly, the original queries may not be suitable for precise retrieval, resulting in erroneous contextual knowledge; Secondly, the language model can easily generate inconsistent answer with external references due to their knowledge boundary limitation. To address these issues, we propose the chain-of-verification (CoV-RAG) to enhance the external retrieval correctness and internal generation consistency. Specifically, we integrate the verification module into the RAG, engaging in scoring, judgment, and rewriting. To correct external retrieval errors, CoV-RAG retrieves new knowledge using a revised query. To correct internal generation errors, we unify QA and verification tasks with a Chain-of-Thought (CoT) reasoning during training. Our comprehensive experiments across various LLMs demonstrate the effectiveness and adaptability compared with other strong baselines. Especially, our CoV-RAG can significantly surpass the state-of-the-art baselines using different LLM backbones.
2020
Don’t Eclipse Your Arts Due to Small Discrepancies: Boundary Repositioning with a Pointer Network for Aspect Extraction
Zhenkai Wei
|
Yu Hong
|
Bowei Zou
|
Meng Cheng
|
Jianmin Yao
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
The current aspect extraction methods suffer from boundary errors. In general, these errors lead to a relatively minor difference between the extracted aspects and the ground-truth. However, they hurt the performance severely. In this paper, we propose to utilize a pointer network for repositioning the boundaries. Recycling mechanism is used, which enables the training data to be collected without manual intervention. We conduct the experiments on the benchmark datasets SE14 of laptop and SE14-16 of restaurant. Experimental results show that our method achieves substantial improvements over the baseline, and outperforms state-of-the-art methods.
Search
Co-authors
- Bolei He 1
- Nuo Chen 1
- Xinran He 1
- Lingyong Yan 1
- Jinchang Luo 1
- show all...