Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuning
Retrieval-Augmented Generation (RAG) offers an effective solution to the issues faced by Large Language Models (LLMs) in hallucination generation and knowledge obsolescence by incorporating externally retrieved knowledge. However, existing methods lack effective control mechanisms for integrating internal and external knowledge. Inspired by human cognitive processes, we propose Parenting, a novel framework that decouples, identifies, and purposefully optimizes parameter subspaces related to adherence and robustness. Specifically, Parenting utilizes a key parameter mining method that combines forward and backward propagation signals to localize subspaces representing different capabilities. Then, Parenting employs a type-tailored tuning strategy, applying specific and appropriate optimizations to different subspaces, aiming to achieve a balanced enhancement of both adherence and robustness. Extensive experiments on various datasets and models validate the effectiveness and generalizability of our method.
Code (0)
등록된 구현이 없습니다.
Tasks
HallucinationRAGRetrievalRetrieval-augmented GenerationSimilar Papers 제목 키워드 기반
Optimizing Knowledge Integration in Retrieval-Augmented Generation with Self-Selection
Retrieval-Augmented Generation (RAG), which integrates external knowledge into Large Language Models (LLMs), has proven effective in enabling LLMs to produce more accurate and reliable responses. However, it remains a si…
Natural QuestionsRAGRetrievalRetrieval-augmented GenerationDirect Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models
Retrieval-augmented generation (RAG) integrates large language models ( LLM s) with retrievers to access external knowledge, improving the factuality of LLM generation in knowledge-grounded tasks. To optimize the RAG per…
Policy Gradient MethodsRAGRetrievalRetrieval-augmented GenerationContext-Augmented Code Generation Using Programming Knowledge Graphs
Large Language Models (LLMs) and Code-LLMs (CLLMs) have significantly improved code generation, but, they frequently face difficulties when dealing with challenging and complex problems. Retrieval-Augmented Generation (R…
Code GenerationHumanEvalKnowledge Graphsmbpp+4Unanswerability Evaluation for Retrieval Augmented Generation
Existing evaluation frameworks for retrieval-augmented generation (RAG) systems focus on answerable queries, but they overlook the importance of appropriately rejecting unanswerable requests. In this paper, we introduce …
RAGRetrievalRetrieval-augmented GenerationHow Does Knowledge Selection Help Retrieval Augmented Generation?
Retrieval-augmented generation (RAG) is a powerful method for enhancing natural language generation by integrating external knowledge into a model's output. While prior work has demonstrated the importance of improving k…
RAGRetrievalRetrieval-augmented GenerationText Generation