ConTReGen: Context-driven Tree-structured Retrieval for Open-domain Long-form Text Generation
Open-domain long-form text generation requires generating coherent, comprehensive responses that address complex queries with both breadth and depth. This task is challenging due to the need to accurately capture diverse facets of input queries. Existing iterative retrieval-augmented generation (RAG) approaches often struggle to delve deeply into each facet of complex queries and integrate knowledge from various sources effectively. This paper introduces ConTReGen, a novel framework that employs a context-driven, tree-structured retrieval approach to enhance the depth and relevance of retrieved content. ConTReGen integrates a hierarchical, top-down in-depth exploration of query facets with a systematic bottom-up synthesis, ensuring comprehensive coverage and coherent integration of multifaceted information. Extensive experiments on multiple datasets, including LFQA and ODSUM, alongside a newly introduced dataset, ODSUM-WikiHow, demonstrate that ConTReGen outperforms existing state-of-the-art RAG models.
Code (0)
등록된 구현이 없습니다.
Tasks
FormRAGRetrievalRetrieval-augmented GenerationText GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Structured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval
The current state-of-the-art image-sentence retrieval methods implicitly align the visual-textual fragments, like regions in images and words in sentences, and adopt attention modules to highlight the relevance of cross-…
cross-modal alignmentRetrievalSemantic correspondenceSentence+1Deriving Character Logic from Storyline as Codified Decision Trees
Role-playing (RP) agents rely on behavioral profiles to act consistently across diverse narrative contexts, yet existing profiles are largely unstructured, non-executable, and weakly validated, leading to brittle agent b…
HDSL: A Hierarchical Domain-Specific Language for Structured 3D Indoor Scene Generation and Localized Editing with LLM Agents
Text-driven indoor scene generation and editing require an intermediate representation that language models can both produce and revise. Existing LLM-based systems often rely on scene graphs or global constraint lists, w…
Scene GenerationProgram RepairPersonaTree: Structured Lifecycle Memory for Person Understanding in LLM Agents
Persistent LLM agents require memory representations that make the formation of person understanding explicit across long term interaction. Existing agent memory methods emphasize information retention and retrieval, yet…
Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents
Long-horizon conversational agents need to interact with users through evolving events, tasks, and goals. Such histories are naturally temporal, yet many existing memory systems organize information primarily by topical …