paper-with-me

홈 › Papers

DOTRAG: Retrieval-Time Reasoning Along Paths

2026-04-06 · Larnell Moore, Naihao Deng, Rada Mihalcea, Farnaz Jahanbakhsh arxiv

Graph Retrieval-Augmented Generation (GraphRAG) is dominated by a retrieve-then-reason paradigm, where context is retrieved using heuristics and then reasoned over. Such methods struggle to adapt to the query-specific logic required for complex multi-hop tasks, often accumulating irrelevant context or missing correct relational paths. We propose DotRAG, a training-free GraphRAG framework that reformulates retrieval as a reasoning process over paths. Our approach generates query-conditioned constraints that guide graph exploration, prune irrelevant regions, and iteratively discover relational paths without relying on explicit step-by-step reasoning chains. We introduce Division of Thought (DOT), an abstraction that decomposes retrieval into localized search spaces and adapts the search strategy to each query. DotRAG achieves SOTA performance on MetaQA and UltraDomain, with consistent gains on multi-hop tasks, demonstrating the effectiveness of reasoning-guided retrieval.

📄 PDF Abstract BibTeX arXiv:2605.18760

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models

2024-10-16 · Linhao Luo, Zicheng Zhao, Chen Gong, Gholamreza Haffari 외

Large language models (LLMs) have demonstrated impressive reasoning abilities, but they still struggle with faithful reasoning due to knowledge gaps and hallucinations. To address these issues, knowledge graphs (KGs) hav…

HallucinationKnowledge Graphs

FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering

2024-05-22 · Yuan Sui, Yufei He, Nian Liu, Xiaoxin He 외

Large language models are often challenged by generating erroneous or `hallucinated' responses, especially in complex reasoning tasks. To mitigate this, we propose a retrieval augmented reasoning method, FiDeLiS, which e…

Common Sense ReasoningGraph Question AnsweringKnowledge GraphsLanguage Modeling+5

Encoder-Free Knowledge-Graph Reasoning with LLMs via Hyperdimensional Path Retrieval

2025-12-10 · Yezi Liu, William Youngwoo Chung, Hanning Chen, Calvin Yeung 외 arxiv

Recent progress in large language models (LLMs) has made knowledge-grounded reasoning increasingly practical, yet KG-based QA systems often pay a steep price in efficiency and transparency. In typical pipelines, symbolic…

PrLM: Learning Explicit Reasoning for Personalized RAG via Contrastive Reward Optimization

2025-08-10 · Kepu Zhang, Teng Shi, Weijie Yu, Jun Xu arxiv

Personalized retrieval-augmented generation (RAG) aims to produce user-tailored responses by incorporating retrieved user profiles alongside the input query. Existing methods primarily focus on improving retrieval and re…

Reinforcement LearningText Generation

Enhancing Large Language Models with Reward-guided Tree Search for Knowledge Graph Question and Answering

2025-05-18 · Xiao Long, Liansheng Zhuang, Chen Shen, Shaotian Yan 외

Recently, large language models (LLMs) have demonstrated impressive performance in Knowledge Graph Question Answering (KGQA) tasks, which aim to find answers based on knowledge graphs (KGs) for natural language questions…

Graph Question AnsweringKnowledge GraphsQuestion AnsweringRetrieval+1