RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913379755491328 |
|---|---|
| author | Liu, Yanming Peng, Xinyue Zhang, Xuhong Liu, Weihao Yin, Jianwei Cao, Jiannan Du, Tianyu |
| author_facet | Liu, Yanming Peng, Xinyue Zhang, Xuhong Liu, Weihao Yin, Jianwei Cao, Jiannan Du, Tianyu |
| contents | Large language models (LLMs) demonstrate exceptional performance in numerous tasks but still heavily rely on knowledge stored in their parameters. Moreover, updating this knowledge incurs high training costs. Retrieval-augmented generation (RAG) methods address this issue by integrating external knowledge. The model can answer questions it couldn't previously by retrieving knowledge relevant to the query. This approach improves performance in certain scenarios for specific tasks. However, if irrelevant texts are retrieved, it may impair model performance. In this paper, we propose Retrieval Augmented Iterative Self-Feedback (RA-ISF), a framework that iteratively decomposes tasks and processes them in three submodules to enhance the model's problem-solving capabilities. Experiments show that our method outperforms existing benchmarks, performing well on models like GPT3.5, Llama2, significantly enhancing factual reasoning capabilities and reducing hallucinations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_06840 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback Liu, Yanming Peng, Xinyue Zhang, Xuhong Liu, Weihao Yin, Jianwei Cao, Jiannan Du, Tianyu Computation and Language Artificial Intelligence Large language models (LLMs) demonstrate exceptional performance in numerous tasks but still heavily rely on knowledge stored in their parameters. Moreover, updating this knowledge incurs high training costs. Retrieval-augmented generation (RAG) methods address this issue by integrating external knowledge. The model can answer questions it couldn't previously by retrieving knowledge relevant to the query. This approach improves performance in certain scenarios for specific tasks. However, if irrelevant texts are retrieved, it may impair model performance. In this paper, we propose Retrieval Augmented Iterative Self-Feedback (RA-ISF), a framework that iteratively decomposes tasks and processes them in three submodules to enhance the model's problem-solving capabilities. Experiments show that our method outperforms existing benchmarks, performing well on models like GPT3.5, Llama2, significantly enhancing factual reasoning capabilities and reducing hallucinations. |
| title | RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2403.06840 |