Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.09916 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912030272782336 |
|---|---|
| author | Nguyen, Xuan-Phi Pandit, Shrey Purushwalkam, Senthil Xu, Austin Chen, Hailin Ming, Yifei Ke, Zixuan Savarese, Silvio Xong, Caiming Joty, Shafiq |
| author_facet | Nguyen, Xuan-Phi Pandit, Shrey Purushwalkam, Senthil Xu, Austin Chen, Hailin Ming, Yifei Ke, Zixuan Savarese, Silvio Xong, Caiming Joty, Shafiq |
| contents | Retrieval Augmented Generation (RAG), a paradigm that integrates external contextual information with large language models (LLMs) to enhance factual accuracy and relevance, has emerged as a pivotal area in generative AI. The LLMs used in RAG applications are required to faithfully and completely comprehend the provided context and users' questions, avoid hallucination, handle unanswerable, counterfactual or otherwise low-quality and irrelevant contexts, perform complex multi-hop reasoning and produce reliable citations. In this paper, we introduce SFR-RAG, a small LLM that is instruction-tuned with an emphasis on context-grounded generation and hallucination minimization. We also present ContextualBench, a new evaluation framework compiling multiple popular and diverse RAG benchmarks, such as HotpotQA and TriviaQA, with consistent RAG settings to ensure reproducibility and consistency in model assessments. Experimental results demonstrate that our SFR-RAG-9B model outperforms leading baselines such as Command-R+ (104B) and GPT-4o, achieving state-of-the-art results in 3 out of 7 benchmarks in ContextualBench with significantly fewer parameters. The model is also shown to be resilient to alteration in the contextual information and behave appropriately when relevant context is removed. Additionally, the SFR-RAG model maintains competitive performance in general instruction-following tasks and function-calling capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_09916 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SFR-RAG: Towards Contextually Faithful LLMs Nguyen, Xuan-Phi Pandit, Shrey Purushwalkam, Senthil Xu, Austin Chen, Hailin Ming, Yifei Ke, Zixuan Savarese, Silvio Xong, Caiming Joty, Shafiq Computation and Language Artificial Intelligence Retrieval Augmented Generation (RAG), a paradigm that integrates external contextual information with large language models (LLMs) to enhance factual accuracy and relevance, has emerged as a pivotal area in generative AI. The LLMs used in RAG applications are required to faithfully and completely comprehend the provided context and users' questions, avoid hallucination, handle unanswerable, counterfactual or otherwise low-quality and irrelevant contexts, perform complex multi-hop reasoning and produce reliable citations. In this paper, we introduce SFR-RAG, a small LLM that is instruction-tuned with an emphasis on context-grounded generation and hallucination minimization. We also present ContextualBench, a new evaluation framework compiling multiple popular and diverse RAG benchmarks, such as HotpotQA and TriviaQA, with consistent RAG settings to ensure reproducibility and consistency in model assessments. Experimental results demonstrate that our SFR-RAG-9B model outperforms leading baselines such as Command-R+ (104B) and GPT-4o, achieving state-of-the-art results in 3 out of 7 benchmarks in ContextualBench with significantly fewer parameters. The model is also shown to be resilient to alteration in the contextual information and behave appropriately when relevant context is removed. Additionally, the SFR-RAG model maintains competitive performance in general instruction-following tasks and function-calling capabilities. |
| title | SFR-RAG: Towards Contextually Faithful LLMs |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2409.09916 |