Jul 2026· Annual International ACM SIGIR Conference on Research and Development in Information Retrieval· pp. 5314-5314· 0 citations· 4 references
Computer Science
TL;DR
This thesis investigates principled and efficient continual learning mechanisms for GR under these realistic conditions, with a unifying hypothesis that scalable and efficient retriever adaptation is essential to maintaining effective GR.
Abstract
Generative Retrieval (GR) encompasses two primary paradigms: Generative Document Retrieval (GDR), which directly generates document identifiers, and Retrieval-Augmented Generation (RAG), which synthesizes reliable responses from retrieved evidence. Despite their promising performance, most existing GR approaches assume static corpora. In GDR, corpus knowledge is encoded directly into model parameters, meaning that integrating new documents requires expensive retraining while risking catastrophic forgetting. Non-stationarity also arises along the temporal dimension: in RAG systems, facts evolve and queries frequently contain temporal constraints. When temporally misaligned evidence is retrieved, generation quality degrades regardless of the LLM's reasoning capability, demonstrating that the retriever forms a central bottleneck under evolving knowledge. Beyond textual corpora, modern Information Retrieval (IR) increasingly operates over multimodal collections that combine text, images, and other modalities. These corpora are likewise dynamic and subject to continuous distributional shifts. In summary, real-world information retrieval systems are characterized by multiple forms of non-stationarity: text corpus growth, temporal evolution, and multimodal corpus growth. This thesis investigates principled and efficient continual learning (CL) mechanisms for GR under these realistic conditions, with a unifying hypothesis that scalable and efficient retriever adaptation is essential to maintaining effective GR.
Generative Retrieval (GR) models map queries directly to document identifiers, replacing conventional retrieval over external sparse or dense indexes with autoregressive identifier generation. However, most generative retrieval frameworks rely on a single-identifier assumption, mapping each document to a single target sequence. This forces the model to represent all document content with one sequence. Since documents are often multi-faceted, this can lead to lossy representations and reduced robustness to query variation, where multiple query intents must compete for a single generative access path. In this work, we introduce Passage-Driven Multi-ID Retrieval (PDMR), a generative retrieval framework that represents documents through multiple passage-level identifiers. PDMR segments each document and assigns one identifier to each selected passage, which provides multiple semantic entry points for retrieving the same document. This multi-entry representation allows the model to align queries with specific semantic facets, thereby reducing the dependence on a single document-level target. To address the supervision ambiguity of this one-to-many mapping, we formulate training as a multi-target learning problem and explore an objective function designed to distribute probability mass across multiple valid passage-level identifiers. We evaluate PDMR on NQ320K and MS MARCO Document. On NQ320K, PDMR improves over strong generative and non-generative baselines on Recall@1 and MRR@100. On MS MARCO Document, PDMR achieves the best Recall@1 and MRR@10 among the reported methods, while remaining competitive on Recall@10. Controlled ablations further show that passage-level supervision, identifier design, training-query augmentation, and multi-target learning contribute complementary gains.
Traditional search engine returns ranked lists for humans to interpret. Retrieval Augmented Generation pipelines go further, feeding retrieved context directly into large language models to synthesize knowledge rather than simply surface it. This study addresses a focused question: When the generative layer is held constant, how do distinct retrieval architectures perform across diverse query types? We fix the LLM and chunking strategy while independently varying the retrieval backend and embedding model across three configurations: Memory Resident Specialist (MRS), Industrial Semantic Index (ISI), and Agile Hybrid Scaler (AHS) evaluated over a six-tier query taxonomy. Our results demonstrate that retrieval quality acts as a rigid performance ceiling for generative correctness. Notably, the "Efficiency Paradox" emerged: the AHS configuration, leveraging lightweight MiniLM embeddings with Pinecone cloud indexing, achieved parity with proprietary high-dimensional configurations on complex logical reasoning tasks. However, all three architectures share a critical weakness for conversational queries. Multi-turn contexts revealed a systemic failure stemming from the absence of anaphora resolution in naive RAG pipelines. These findings suggest that for RAG applications, strategic database indexing is a more critical performance lever than embedding parameter scale: architectural retrieval decisions matter more than model size.
Assmaa Moutaoukkil, Ali El Mezouary, A. Idarrou et al.· EPJ Web of Conferences· 0 citations
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external information, but traditional fixed retrieval processes struggle to adapt to complex task requirements. In recent years, reinforcement learning (RL) has been increasingly applied to train LLMs to autonomously invoke search tools, driving RAG to evolve from the passive information acquisition of a fixed pipeline to a trustworthy retrieval system with autonomous decision-making capabilities. This paper reviews the representative studies on the combination of LLMs, RAG and RL in recent years. It focuses on analyzing the role of RL in dynamic retrieval, process rewards, query optimization, etc., and compares the connections and evolutionary relationships among different methods. The research findings show that RL has gradually expanded from simply improving the accuracy of the final answer to optimizing queries, multi-round search, process decision-making and trustworthy screening, providing new ideas for enhancing the active retrieval ability of RAG and improving the credibility of information.
Zun-Long Hong· Applied and Computational En...· 0 citations
This paper presents a technical synthesis of RAG for trustworthy enterprise assistants and describes the end-to-end pipeline in full: document chunking, embedding, vector indexing, retrieval, cross-encoder re-ranking, and grounded generation with inline citations.
Bini P. B.· International Journal of Inf...· 0 citations
Empirical evaluations across a diverse suite of multimodal document retrieval benchmarks reveal that DART achieves consistent and significant gains in ranking precision, and this dynamic refinement process introduces minimal computational latency, offering a highly efficient, plug-and-play solution for adaptive document retrieval.
Jing Zhang, Yaowei Wang, Chongyu Wang et al.· International Conference on...· 0 citations
Although multi-turn inference remains more expensive than single-call retrieval, VecTree-RAG provides a structure-aware and traceable architecture for scientific literature question answering.
