paper-with-me

Papers

STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBack

2024-10-14 · Naman Gupta, Shashank Kirtania, Priyanshu Gupta, Krishna Kariya, Sumit Gulwani, Arun Iyer, Suresh Parthasarathy, Arjun Radhakrishna, Sriram K. Rajamani, Gustavo Soares

Large Language Models (LLMs) often generate incorrect or outdated information, especially in low-resource settings or when dealing with private data. To address this, Retrieval-Augmented Generation (RAG) uses external knowledge bases (KBs), but these can also suffer from inaccuracies. We introduce STACKFEED, a novel Structured Textual Actor-Critic Knowledge base editing with FEEDback approach that iteratively refines the KB based on expert feedback using a multi-actor, centralized critic reinforcement learning framework. Each document is assigned to an actor, modeled as a ReACT agent, which performs structured edits based on document-specific targeted instructions from a centralized critic. Experimental results show that STACKFEED significantly improves KB quality and RAG system performance, enhancing accuracy by up to 8% over baselines.

📄 PDF Abstract BibTeX arXiv:2410.10584

Code (0)

등록된 구현이 없습니다.

Tasks

RAGRetrievalRetrieval-augmented Generation

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 &…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
WordPiece 설명 없음
Residual Connection 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

ConTextual: Improving Clinical Text Summarization in LLMs with Context-preserving Token Filtering and Knowledge Graphs

2025-04-23 · Fahmida Liza Piya, Rahmatollah Beheshti

Unstructured clinical data can serve as a unique and rich source of information that can meaningfully inform clinical practice. Extracting the most pertinent context from such data is critical for exploiting its true pot…

Decision MakingKnowledge GraphsText GenerationText Summarization

Structural Knowledge Distillation: Tractably Distilling Information for Structured Predictor

2020-10-10 · ACL 2021 5 · Xinyu Wang, Yong Jiang, Zhaohui Yan, Zixia Jia 외

Knowledge distillation is a critical technique to transfer knowledge between models, typically from a large model (the teacher) to a more fine-grained one (the student). The objective function of knowledge distillation i…

Dependency ParsingKnowledge DistillationStructured Prediction

GraphDiffs: Graph Modeling with Differential Sequence for Document-Grounded Conversation

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Knowledge grounded dialogue systems need to incorporate natural transitions between knowledge for dialogue to flow smoothly. Current systems not only lack good structured representations for knowledge that span multiple …

Uncovering Context Reliance in Unstructured Knowledge Editing

2026-02-22 · Zisheng Zhou, Mengqi Zhang, Shiguang Wu, Xiaotian Ye 외 arxiv

Editing Large language models (LLMs) with real-world, unstructured knowledge is essential for correcting and updating their internal parametric knowledge. In this work, we revisit the fundamental next-token prediction (N…

knowledge editing

HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases

2024-12-20 · Meng-Chieh Lee, Qi Zhu, Costas Mavromatis, Zhen Han 외

Given a semi-structured knowledge base (SKB), where text documents are interconnected by relations, how can we effectively retrieve relevant information to answer user questions? Retrieval-Augmented Generation (RAG) retr…

Question AnsweringRAGRetrievalRetrieval-augmented Generation