paper-with-me

홈 › Papers

RAFT: Adapting Language Model to Domain Specific RAG

2024-03-15 · Tianjun Zhang, Shishir G. Patil, Naman jain, Sheng Shen, Matei Zaharia, Ion Stoica, Joseph E. Gonzalez

Pretraining Large Language Models (LLMs) on large corpora of textual data is now a standard paradigm. When using these LLMs for many downstream applications, it is common to additionally bake in new knowledge (e.g., time-critical news, or private domain knowledge) into the pretrained model either through RAG-based-prompting, or fine-tuning. However, the optimal methodology for the model to gain such new knowledge remains an open question. In this paper, we present Retrieval Augmented FineTuning (RAFT), a training recipe that improves the model's ability to answer questions in a "open-book" in-domain settings. In RAFT, given a question, and a set of retrieved documents, we train the model to ignore those documents that don't help in answering the question, which we call, distractor documents. RAFT accomplishes this by citing verbatim the right sequence from the relevant document that would help answer the question. This coupled with RAFT's chain-of-thought-style response helps improve the model's ability to reason. In domain-specific RAG, RAFT consistently improves the model's performance across PubMed, HotpotQA, and Gorilla datasets, presenting a post-training recipe to improve pre-trained LLMs to in-domain RAG. RAFT's code and demo are open-sourced at github.com/ShishirPatil/gorilla.

📄 PDF Abstract BibTeX arXiv:2403.10131

Code (1)

ShishirPatil/gorilla 공식 구현 tf

Tasks

Language ModelingLanguage ModellingmodelRAG

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Multi-Head Attention 설명 없음
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Training Domain Draft Models for Speculative Decoding: Best Practices and Insights

2025-03-10 · Fenglu Hong, Ravi Raju, Jonathan Lingjie Li, Bo Li 외

Speculative decoding is an effective method for accelerating inference of large language models (LLMs) by employing a small draft model to predict the output of a target model. However, when adapting speculative decoding…

Knowledge Distillation

Reformulating Domain Adaptation of Large Language Models as Adapt-Retrieve-Revise: A Case Study on Chinese Legal Domain

2023-10-05 · Zhen Wan, Yating Zhang, Yexiang Wang, Fei Cheng 외

While large language models (LLMs) like GPT-4 have recently demonstrated astonishing zero-shot capabilities in general domain tasks, they often generate content with hallucinations in specific domains such as Chinese law…

Domain Adaptation

Cascade Prompt Learning for Vision-Language Model Adaptation

2024-09-26 · Ge Wu, Xin Zhang, Zheng Li, Zhaowei Chen 외

Prompt learning has surfaced as an effective approach to enhance the performance of Vision-Language Models (VLMs) like CLIP when applied to downstream tasks. However, current learnable prompt tokens are primarily used fo…

General Knowledgeimage-classificationImage ClassificationLanguage Modeling+3

Transfer Learning for Clinical Time Series Analysis using Deep Neural Networks

2019-04-01 · Priyanka Gupta, Pankaj Malhotra, Jyoti Narwariya, Lovekesh Vig 외

Deep neural networks have shown promising results for various clinical prediction tasks. However, training deep networks such as those based on Recurrent Neural Networks (RNNs) requires large labeled data, significant hy…

Domain AdaptationTime SeriesTime Series AnalysisTransfer Learning

Examples as the Prompt: A Scalable Approach for Efficient LLM Adaptation in E-Commerce

2025-03-14 · Jingying Zeng, Zhenwei Dai, Hui Liu, Samarth Varshney 외

Prompting LLMs offers an efficient way to guide output generation without explicit model training. In the e-commerce domain, prompting-based applications are widely used for tasks such as query understanding, recommender…

Prompt EngineeringRecommendation Systems