Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Together
원문 초록
Natural Language Processing (NLP) systems are increasingly taking the form of sophisticated modular pipelines, e.g., Retrieval Augmented Generation (RAG), where each module may involve a distinct Language Model (LM) and an associated prompt template. These compound systems often lack intermediate labels or gradient flow to optimize each module, making their end-to-end optimization challenging. Here we seek strategies to optimize both the module-level LM weights and the associated prompt templates of such systems to maximize a downstream task metric. We propose for the first time combining the weight and prompt optimization strategies to optimize a modular LM pipeline by alternating between the two to get the same LM to teach itself. In experiments with multi-hop QA, mathematical reasoning, and feature-based classification using mistral-7b, llama-2-7b, and llama-3-8b, these BetterTogether strategies optimizing the weights and prompts of a pipeline together outperform directly optimizing weights alone and prompts alone by up to 60% and 6%, respectively, on average across LMs and tasks. BetterTogether optimizer is released in DSPy at http://dspy.ai
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Lightweight Relevance Grader in RAG
FlexRAG: A Flexible and Comprehensive Framework for Retrieval-Augmented Generation
NeuralNexus at BEA 2025 Shared Task: Retrieval-Augmented Prompting for Mistake Identification in AI Tutors
Bridging the Gap Between Open-Source and Proprietary LLMs in Table QA
XGraphRAG: Interactive Visual Analysis for Graph-based Retrieval-Augmented Generation
KisMATH: Do LLMs Have Knowledge of Implicit Structures in Mathematical Reasoning?
토론
이 논문과 연결된 포럼 글이 아직 없습니다.