Multi-Step Semantic Reasoning in Generative Retrieval

• URL: http://arxiv.org/abs/2603.12368v1
• Date: Thu, 12 Mar 2026 18:38:50 GMT
• Title: Multi-Step Semantic Reasoning in Generative Retrieval
• Abstract summary: Generative retrieval (GR) models encode a corpus within model parameters and generate relevant document identifiers for a given query.<n>Existing GR models struggle with complex queries in numerical contexts, such as those involving semantic reasoning over financial reports.<n>We propose ReasonGR, a framework designed to enhance multi-step semantic reasoning in numerical contexts within GR.
• Score: 50.65947993017158
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative retrieval (GR) models encode a corpus within model parameters and generate relevant document identifiers directly for a given query. While this paradigm shows promise in retrieval tasks, existing GR models struggle with complex queries in numerical contexts, such as those involving semantic reasoning over financial reports, due to limited reasoning capabilities. This limitation leads to suboptimal retrieval accuracy and hinders practical applicability. We propose ReasonGR, a framework designed to enhance multi-step semantic reasoning in numerical contexts within GR. ReasonGR employs a structured prompting strategy combining task-specific instructions with stepwise reasoning guidance to better address complex retrieval queries. Additionally, it integrates a reasoning-focused adaptation module to improve the learning of reasoning-related parameters. Experiments on the FinQA dataset, which contains financial queries over complex documents, demonstrate that ReasonGR improves retrieval accuracy and consistency, indicating its potential for advancing GR models in reasoning-intensive retrieval scenarios.

Related papers

• GEM: A Generative Embedding Model Bridging Reasoning and Retrieval [15.116615102031771]
  We present GEM, a generative embedding model that augments retrieval through its own knowledge.<n> evaluated on reasoning-intensive and instruction-following retrieval tasks.<n> GEM's generative nature allows test-time compute scaling via prompting to further enhance retrieval performance.
  arXiv  Detail & Related papers  (2026-08-13T13:03:49Z)
• Stepwise Reasoning Enhancement for LLMs via External Subgraph Generation [10.192419467718475]
  Large language models struggle with logical consistency, factual grounding, and interpretability in complex multi-step reasoning.<n>This paper proposes SGR, a framework that integrates large language models with external knowledge graphs.<n> Experiments show that SGR improves reasoning accuracy and Hits@1 performance over standard prompting.
  arXiv  Detail & Related papers  (2026-06-03T04:58:02Z)
• ROG: Retrieval-Augmented LLM Reasoning for Complex First-Order Queries over Knowledge Graphs [14.25887925588904]
  We propose a retrieval-augmented framework that combines query-aware neighborhood retrieval with large language model (LLM) chain-of-thought reasoning.<n>ROG decomposes a multi-operator query into a sequence of single-operator sub-queries.<n> Intermediate answer sets are cached and reused across steps, improving consistency on deep reasoning chains.
  arXiv  Detail & Related papers  (2026-02-02T17:45:43Z)
• Query, Decompose, Compress: Structured Query Expansion for Efficient Multi-Hop Retrieval [19.37201042661162]
  Large Language Models (LLMs) have been increasingly employed for query expansion.<n>DeCoR (Decompose and Compress for Retrieval) is a framework grounded in structured information refinement.
  arXiv  Detail & Related papers  (2026-01-14T05:55:49Z)
• A Large Language Model Based Method for Complex Logical Reasoning over Knowledge Graphs [16.929901817693334]
  Reasoning over knowledge graphs (KGs) with first-order logic (FOL) queries is challenging due to the inherent incompleteness of real-world KGs.<n>We propose ROG (Reasoning Over knowledge Graphs with large language models), an ensemble-style framework that combines query-aware KG neighborhood retrieval with large language model (LLM)-based chain-of-thought reasoning.
  arXiv  Detail & Related papers  (2025-12-22T07:01:05Z)
• KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering [64.62317305868264]
  We present textbfKBQA-R1, a framework that shifts the paradigm from text imitation to interaction optimization via Reinforcement Learning.<n>Treating KBQA as a multi-turn decision process, our model learns to navigate the knowledge base using a list of actions.<n>Experiments on WebQSP, GrailQA, and GraphQuestions demonstrate that KBQA-R1 achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-12-10T17:45:42Z)
• RouteRAG: Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement Learning [69.87510139069218]
  Retrieval-Augmented Generation (RAG) integrates non-parametric knowledge into Large Language Models (LLMs)<n>Recent progress has advanced text-based RAG to multi-turn reasoning through Reinforcement Learning (RL)<n>We introduce model, an RL-based framework that enables LLMs to perform multi-turn and adaptive graph-text hybrid RAG.
  arXiv  Detail & Related papers  (2025-12-10T10:05:31Z)
• Towards Context-aware Reasoning-enhanced Generative Searching in E-commerce [61.03081096959132]
  We propose a context-aware reasoning-enhanced generative search framework for better textbfunderstanding the complicated context.<n>Our approach achieves superior performance compared with strong baselines, validating its effectiveness for search-based recommendation.
  arXiv  Detail & Related papers  (2025-10-19T16:46:11Z)
• Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding [61.36285696607487]
  Document understanding is critical for applications from financial analysis to scientific discovery.<n>Current approaches, whether OCR-based pipelines feeding Large Language Models (LLMs) or native Multimodal LLMs (MLLMs) face key limitations.<n>Retrieval-Augmented Generation (RAG) helps ground models in external data, but documents' multimodal nature, combining text, tables, charts, and layout, demands a more advanced paradigm: Multimodal RAG.
  arXiv  Detail & Related papers  (2025-10-17T02:33:16Z)
• Reasoning-enhanced Query Understanding through Decomposition and Interpretation [87.56450566014625]
  ReDI is a Reasoning-enhanced approach for query understanding through Decomposition and Interpretation.<n>We compiled a large-scale dataset of real-world complex queries from a major search engine.<n> Experiments on BRIGHT and BEIR demonstrate that ReDI consistently surpasses strong baselines in both sparse and dense retrieval paradigms.
  arXiv  Detail & Related papers  (2025-09-08T10:58:42Z)
• Resource-Friendly Dynamic Enhancement Chain for Multi-Hop Question Answering [21.077964610022313]
  This work proposes a novel framework called DEC (Dynamic Enhancement Chain)<n> DEC first decomposes complex questions into logically coherent subquestions to form a hallucination-free reasoning chain.<n>It then iteratively refines these subquestions through context-aware rewriting to generate effective query formulations.
  arXiv  Detail & Related papers  (2025-06-21T11:55:27Z)
• Modeling Relational Patterns for Logical Query Answering over Knowledge Graphs [29.47155614953955]
  We develop a novel query embedding method, RoConE, that defines query regions as geometric cones and algebraic query operators by rotations in complex space.<n>Our experimental results on several benchmark datasets confirm the advantage of relational patterns for enhancing logical query answering task.
  arXiv  Detail & Related papers  (2023-03-21T13:59:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.