Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.20871 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915307179737088 |
|---|---|
| author | Sun, Xin Xie, Jianan Chen, Zhongqi Liu, Qiang Wu, Shu Chen, Yuehe Song, Bowen Wang, Weiqiang Wang, Zilei Wang, Liang |
| author_facet | Sun, Xin Xie, Jianan Chen, Zhongqi Liu, Qiang Wu, Shu Chen, Yuehe Song, Bowen Wang, Weiqiang Wang, Zilei Wang, Liang |
| contents | Large language models (LLMs) augmented with retrieval systems have significantly advanced natural language processing tasks by integrating external knowledge sources, enabling more accurate and contextually rich responses. To improve the robustness of such systems against noisy retrievals, Retrieval-Augmented Fine-Tuning (RAFT) has emerged as a widely adopted method. However, RAFT conditions models to generate answers even in the absence of reliable knowledge. This behavior undermines their reliability in high-stakes domains, where acknowledging uncertainty is critical. To address this issue, we propose Divide-Then-Align (DTA), a post-training approach designed to endow RAG systems with the ability to respond with "I don't know" when the query is out of the knowledge boundary of both the retrieved passages and the model's internal knowledge. DTA divides data samples into four knowledge quadrants and constructs tailored preference data for each quadrant, resulting in a curated dataset for Direct Preference Optimization (DPO). Experimental results on three benchmark datasets demonstrate that DTA effectively balances accuracy with appropriate abstention, enhancing the reliability and trustworthiness of retrieval-augmented systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_20871 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG Sun, Xin Xie, Jianan Chen, Zhongqi Liu, Qiang Wu, Shu Chen, Yuehe Song, Bowen Wang, Weiqiang Wang, Zilei Wang, Liang Computation and Language Large language models (LLMs) augmented with retrieval systems have significantly advanced natural language processing tasks by integrating external knowledge sources, enabling more accurate and contextually rich responses. To improve the robustness of such systems against noisy retrievals, Retrieval-Augmented Fine-Tuning (RAFT) has emerged as a widely adopted method. However, RAFT conditions models to generate answers even in the absence of reliable knowledge. This behavior undermines their reliability in high-stakes domains, where acknowledging uncertainty is critical. To address this issue, we propose Divide-Then-Align (DTA), a post-training approach designed to endow RAG systems with the ability to respond with "I don't know" when the query is out of the knowledge boundary of both the retrieved passages and the model's internal knowledge. DTA divides data samples into four knowledge quadrants and constructs tailored preference data for each quadrant, resulting in a curated dataset for Direct Preference Optimization (DPO). Experimental results on three benchmark datasets demonstrate that DTA effectively balances accuracy with appropriate abstention, enhancing the reliability and trustworthiness of retrieval-augmented systems. |
| title | Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2505.20871 |