Dynamic Retrieval-augmented Generation (RAG) has shown great success in mitigating hallucinations in large language models (LLMs) during generation. However, existing dynamic RAG methods face significant limitations in two key aspects: 1) Lack of an effective mechanism to control retrieval triggers, and 2) Lack of effective scrutiny of retrieval content. To address these limitations, we propose an innovative dynamic RAG method, DioR (Adaptive Cognitive Detection and Contextual Retrieval Optimization), which consists of two main components: adaptive cognitive detection and contextual retrieval optimization, specifically designed to determine when retrieval is needed and what to retrieve for LLMs is useful. Experimental results demonstrate that DioR achieves superior performance on all tasks, demonstrating the effectiveness of our work.
Personalization has become an essential capability in modern AI systems, enabling customized interactions that align with individual user preferences, contexts, and goals. Recent research has increasingly concentrated on Retrieval-Augmented Generation (RAG) frameworks and their evolution into more advanced agent-based architectures within personalized settings to enhance user satisfaction. Building on this foundation, this survey systematically examines personalization across the three core stages of RAG: pre-retrieval, retrieval, and generation. Beyond RAG, we further extend its capabilities into the realm of Personalized LLM-based Agents, which enhance traditional RAG systems with agentic functionalities, including user understanding, personalized planning and execution, and dynamic generation. For both personalization in RAG and agent-based personalization, we provide formal definitions, conduct a comprehensive review of recent literature, and summarize key datasets and evaluation metrics. Additionally, we discuss fundamental challenges, limitations, and promising research directions in this evolving field. Relevant papers and resources are continuously updated at https://github.com/Applied-Machine-Learning-Lab/Awesome-Personalized-RAG-Agent.
The rapid evolution of Large Language Models (LLMs) has driven the need for increasingly sophisticated inference pipelines and hardware platforms. Modern LLM serving extends beyond traditional prefill-decode workflows, incorporating multi-stage processes such as Retrieval Augmented Generation (RAG), key-value (KV) cache retrieval, dynamic model routing, and multi step reasoning. These stages exhibit diverse computational demands, requiring distributed systems that integrate GPUs, ASICs, CPUs, and memory-centric architectures. However, existing simulators lack the fidelity to model these heterogeneous, multi-engine workflows, limiting their ability to inform architectural decisions. To address this gap, we introduce HERMES, a Heterogeneous Multi-stage LLM inference Execution Simulator. HERMES models diverse request stages; including RAG, KV retrieval, reasoning, prefill, and decode across complex hardware hierarchies. HERMES supports heterogeneous clients executing multiple models concurrently unlike prior frameworks while incorporating advanced batching strategies and multi-level memory hierarchies. By integrating real hardware traces with analytical modeling, HERMES captures critical trade-offs such as memory bandwidth contention, inter-cluster communication latency, and batching efficiency in hybrid CPU-accelerator deployments. Through case studies, we explore the impact of reasoning stages on end-to-end latency, optimal batching strategies for hybrid pipelines, and the architectural implications of remote KV cache retrieval. HERMES empowers system designers to navigate the evolving landscape of LLM inference, providing actionable insights into optimizing hardware-software co-design for next-generation AI workloads.
Recent advancements in computer vision have highlighted the scalability of Vision Transformers (ViTs) across various tasks, yet challenges remain in balancing adaptability, computational efficiency, and the ability to model higher-order relationships. Vision Graph Neural Networks (ViGs) offer an alternative by leveraging graph-based methodologies but are hindered by the computational bottlenecks of clustering algorithms used for edge generation. To address these issues, we propose the Hypergraph Vision Transformer (HgVT), which incorporates a hierarchical bipartite hypergraph structure into the vision transformer framework to capture higher-order semantic relationships while maintaining computational efficiency. HgVT leverages population and diversity regularization for dynamic hypergraph construction without clustering, and expert edge pooling to enhance semantic extraction and facilitate graph-based image retrieval. Empirical results demonstrate that HgVT achieves strong performance on image classification and retrieval, positioning it as an efficient framework for semantic-based vision tasks.
Large language models (LLMs) have shown promise in automating travel planning, yet they often fall short in addressing nuanced spatiotemporal rationality. While existing benchmarks focus on basic plan validity, they neglect critical aspects such as route efficiency, POI appeal, and real-time adaptability. This paper introduces TP-RAG, the first benchmark tailored for retrieval-augmented, spatiotemporal-aware travel planning. Our dataset includes 2,348 real-world travel queries, 85,575 fine-grain annotated POIs, and 18,784 high-quality travel trajectory references sourced from online tourist documents, enabling dynamic and context-aware planning. Through extensive experiments, we reveal that integrating reference trajectories significantly improves spatial efficiency and POI rationality of the travel plan, while challenges persist in universality and robustness due to conflicting references and noisy data. To address these issues, we propose EvoRAG, an evolutionary framework that potently synergizes diverse retrieved trajectories with LLMs' intrinsic reasoning. EvoRAG achieves state-of-the-art performance, improving spatiotemporal compliance and reducing commonsense violation compared to ground-up and retrieval-augmented baselines. Our work underscores the potential of hybridizing Web knowledge with LLM-driven optimization, paving the way for more reliable and adaptive travel planning agents.
Visual understanding is inherently contextual -- what we focus on in an image depends on the task at hand. For instance, given an image of a person holding a bouquet of flowers, we may focus on either the person such as their clothing, or the type of flowers, depending on the context of interest. Yet, most existing image encoding paradigms represent an image as a fixed, generic feature vector, overlooking the potential needs of prioritizing varying visual information for different downstream use cases. In this work, we introduce FocalLens, a conditional visual encoding method that produces different representations for the same image based on the context of interest, expressed flexibly through natural language. We leverage vision instruction tuning data and contrastively finetune a pretrained vision encoder to take natural language instructions as additional inputs for producing conditional image representations. Extensive experiments validate that conditional image representation from FocalLens better pronounce the visual features of interest compared to generic features produced by standard vision encoders like CLIP. In addition, we show FocalLens further leads to performance improvements on a range of downstream tasks including image-image retrieval, image classification, and image-text retrieval, with an average gain of 5 and 10 points on the challenging SugarCrepe and MMVP-VLM benchmarks, respectively.
The increasing availability of multimodal data across text, tables, and images presents new challenges for developing models capable of complex cross-modal reasoning. Existing methods for Multimodal Multi-hop Question Answering (MMQA) often suffer from limited reasoning capabilities, reliance on modality conversion, and inadequate alignment between visual and textual representations. To address these limitations, this paper introduces Vision-Language Multimodal Transformer (VLMT), a unified architecture that integrates a transformer-based vision encoder with a sequence-to-sequence language model. VLMT employs a direct token-level injection mechanism to fuse visual and textual inputs within a shared embedding space, eliminating the need for intermediate projection layers. To enhance cross-modal alignment and reasoning, a three-stage pretraining strategy is proposed to progressively align vision-language representations and improve the model's capacity for multimodal understanding. Based on the pretrained backbone, two task-specific modules are instantiated to form a two-stage MMQA framework: a multimodal reranker that predicts document relevance scores and utilizes a relative threshold with top-k strategy for context retrieval, and a multimodal question answering model that generates contextually grounded answers based on the retrieved evidence. Comprehensive experiments on two benchmark datasets demonstrate the effectiveness of the proposed approach. On MultimodalQA validation set, VLMT-Large achieves 76.5% Exact Match and 80.1% F1, outperforming the previous state-of-the-art by +9.1% in Exact Match and +8.8% in F1. On WebQA, it attains a QA score of 47.6, surpassing prior models such as PERQA by +3.2. These results highlight VLMT's strong capabilities in multimodal reasoning and its potential to advance real-world information retrieval and question answering systems.
Despite the impressive performance of Retrieval-augmented Generation (RAG) systems across various NLP benchmarks, their robustness in handling real-world user-LLM interaction queries remains largely underexplored. This presents a critical gap for practical deployment, where user queries exhibit greater linguistic variations and can trigger cascading errors across interdependent RAG components. In this work, we systematically analyze how varying four linguistic dimensions (formality, readability, politeness, and grammatical correctness) impact RAG performance. We evaluate two retrieval models and nine LLMs, ranging from 3 to 72 billion parameters, across four information-seeking Question Answering (QA) datasets. Our results reveal that linguistic reformulations significantly impact both retrieval and generation stages, leading to a relative performance drop of up to 40.41% in Recall@5 scores for less formal queries and 38.86% in answer match scores for queries containing grammatical errors. Notably, RAG systems exhibit greater sensitivity to such variations compared to LLM-only generations, highlighting their vulnerability to error propagation due to linguistic shifts. These findings highlight the need for improved robustness techniques to enhance reliability in diverse user interactions.
Recent advances in long-context models (LCMs), designed to handle extremely long input contexts, primarily focus on utilizing external contextual information, often leaving the influence of large language models' intrinsic knowledge underexplored. In this work, we investigate how this intrinsic knowledge affects content generation and demonstrate that its impact becomes increasingly pronounced as context length extends. Furthermore, we show that the model's ability to utilize intrinsic knowledge, which we call intrinsic retrieval ability, does not improve simultaneously with its ability to leverage contextual knowledge through extrinsic retrieval ability. Moreover, better extrinsic retrieval can interfere with the model's ability to use its own knowledge effectively, limiting its full potential. To bridge this gap, we design a simple yet effective Hybrid Needle-in-a-Haystack test that evaluates models based on their capabilities across both retrieval abilities, rather than solely emphasizing extrinsic retrieval ability. Our experimental results reveal that Qwen-2.5 models significantly outperform Llama-3.1 models, demonstrating superior intrinsic retrieval ability. Moreover, even the more powerful Llama-3.1-70B-Instruct model fails to exhibit better performance under LCM conditions, highlighting the importance of evaluating models from a dual-retrieval perspective.
Legal retrieval is a widely studied area in Information Retrieval (IR) and a key task in this domain is retrieving relevant cases based on a given query case, often done by applying language models as encoders to model case similarity. Recently, Tang et al. proposed CaseLink, a novel graph-based method for legal case retrieval, which models both cases and legal charges as nodes in a network, with edges representing relationships such as references and shared semantics. This approach offers a new perspective on the task by capturing higher-order relationships of cases going beyond the stand-alone level of documents. However, while this shift in approaching legal case retrieval is a promising direction in an understudied area of graph-based legal IR, challenges in reproducing novel results have recently been highlighted, with multiple studies reporting difficulties in reproducing previous findings. Thus, in this work we reproduce CaseLink, a graph-based legal case retrieval method, to support future research in this area of IR. In particular, we aim to assess its reliability and generalizability by (i) first reproducing the original study setup and (ii) applying the approach to an additional dataset. We then build upon the original implementations by (iii) evaluating the approach's performance when using a more sophisticated graph data representation and (iv) using an open large language model (LLM) in the pipeline to address limitations that are known to result from using closed models accessed via an API. Our findings aim to improve the understanding of graph-based approaches in legal IR and contribute to improving reproducibility in the field. To achieve this, we share all our implementations and experimental artifacts with the community.
Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for grounding large language models in external knowledge sources, improving the precision of agents responses. However, high-dimensional language model embeddings, often in the range of hundreds to thousands of dimensions, can present scalability challenges in terms of storage and latency, especially when processing massive financial text corpora. This paper investigates the use of Principal Component Analysis (PCA) to reduce embedding dimensionality, thereby mitigating computational bottlenecks without incurring large accuracy losses. We experiment with a real-world dataset and compare different similarity and distance metrics under both full-dimensional and PCA-compressed embeddings. Our results show that reducing vectors from 3,072 to 110 dimensions provides a sizeable (up to $60\times$) speedup in retrieval operations and a $\sim 28.6\times$ reduction in index size, with only moderate declines in correlation metrics relative to human-annotated similarity scores. These findings demonstrate that PCA-based compression offers a viable balance between retrieval fidelity and resource efficiency, essential for real-time systems such as Zanista AI's \textit{Newswitch} platform. Ultimately, our study underscores the practicality of leveraging classical dimensionality reduction techniques to scale RAG architectures for knowledge-intensive applications in finance and trading, where speed, memory efficiency, and accuracy must jointly be optimized.
Retrieval over knowledge graphs is usually performed using dedicated, complex query languages like SPARQL. We propose a novel system, Ontology and Semantic Exploration Toolkit (OnSET) that allows non-expert users to easily build queries with visual user guidance provided by topic modelling and semantic search throughout the application. OnSET allows users without any prior information about the ontology or networked knowledge to start exploring topics of interest over knowledge graphs, including the retrieval and detailed exploration of prototypical sub-graphs and their instances. Existing systems either focus on direct graph explorations or do not foster further exploration of the result set. We, however, provide a node-based editor that can extend on these missing properties of existing systems to support the search over big ontologies with sub-graph instances. Furthermore, OnSET combines efficient and open platforms to deploy the system on commodity hardware.
Long-form video understanding presents significant challenges for interactive retrieval systems, as conventional methods struggle to process extensive video content efficiently. Existing approaches often rely on single models, inefficient storage, unstable temporal search, and context-agnostic reranking, limiting their effectiveness. This paper presents a novel framework to enhance interactive video retrieval through four key innovations: (1) an ensemble search strategy that integrates coarse-grained (CLIP) and fine-grained (BEIT3) models to improve retrieval accuracy, (2) a storage optimization technique that reduces redundancy by selecting representative keyframes via TransNetV2 and deduplication, (3) a temporal search mechanism that localizes video segments using dual queries for start and end points, and (4) a temporal reranking approach that leverages neighboring frame context to stabilize rankings. Evaluated on known-item search and question-answering tasks, our framework demonstrates substantial improvements in retrieval precision, efficiency, and user interpretability, offering a robust solution for real-world interactive video retrieval applications.
Recent advances in large language models (LLMs) provide new opportunities for context understanding in virtual reality (VR). However, VR contexts are often highly localized and personalized, limiting the effectiveness of general-purpose LLMs. To address this challenge, we present RAG-VR, the first 3D question-answering system for VR that incorporates retrieval-augmented generation (RAG), which augments an LLM with external knowledge retrieved from a localized knowledge database to improve the answer quality. RAG-VR includes a pipeline for extracting comprehensive knowledge about virtual environments and user conditions for accurate answer generation. To ensure efficient retrieval, RAG-VR offloads the retrieval process to a nearby edge server and uses only essential information during retrieval. Moreover, we train the retriever to effectively distinguish among relevant, irrelevant, and hard-to-differentiate information in relation to questions. RAG-VR improves answer accuracy by 17.9%-41.8% and reduces end-to-end latency by 34.5%-47.3% compared with two baseline systems.
In recent years, accurately and quickly deploying medical large language models (LLMs) has become a significant trend. Among these, retrieval-augmented generation (RAG) has garnered significant attention due to its features of rapid deployment and privacy protection. However, existing medical RAG frameworks still have shortcomings. Most existing medical RAG frameworks are designed for single-round question answering tasks and are not suitable for multi-round diagnostic dialogue. On the other hand, existing medical multi-round RAG frameworks do not consider the interconnections between potential diseases to inquire precisely like a doctor. To address these issues, we propose a Multi-Round Diagnostic RAG (MRD-RAG) framework that mimics the doctor's diagnostic process. This RAG framework can analyze diagnosis information of potential diseases and accurately conduct multi-round diagnosis like a doctor. To evaluate the effectiveness of our proposed frameworks, we conduct experiments on two modern medical datasets and two traditional Chinese medicine datasets, with evaluations by GPT and human doctors on different methods. The results indicate that our RAG framework can significantly enhance the diagnostic performance of LLMs, highlighting the potential of our approach in medical diagnosis. The code and data can be found in our project website https://github.com/YixiangCh/MRD-RAG/tree/master.
Applications of generative Large Language Models LLMs are rapidly expanding across various domains, promising significant improvements in workflow efficiency and information retrieval. However, their implementation in specialized, high-stakes domains such as hazardous materials transportation is challenging due to accuracy and reliability concerns. This study evaluates the performance of three fine-tuned generative models, ChatGPT, Google's Vertex AI, and ORNL Retrieval Augmented Generation augmented LLaMA 2 and LLaMA in retrieving regulatory information essential for hazardous material transportation compliance in the United States. Utilizing approximately 40 publicly available federal and state regulatory documents, we developed 100 realistic queries relevant to route planning and permitting requirements. Responses were qualitatively rated based on accuracy, detail, and relevance, complemented by quantitative assessments of semantic similarity between model outputs. Results demonstrated that the RAG-augmented LLaMA models significantly outperformed Vertex AI and ChatGPT, providing more detailed and generally accurate information, despite occasional inconsistencies. This research introduces the first known application of RAG in transportation safety, emphasizing the need for domain-specific fine-tuning and rigorous evaluation methodologies to ensure reliability and minimize the risk of inaccuracies in high-stakes environments.
Recently, the personalization of Large Language Models (LLMs) to generate content that aligns with individual user preferences has garnered widespread attention. Personalized Retrieval-Augmented Generation (RAG), which retrieves relevant documents from the user's history to reflect their preferences and enhance LLM generation, is one commonly used approach for personalization. However, existing personalized RAG methods do not consider that the histories of similar users can also assist in personalized generation for the current user, meaning that collaborative information between users can also benefit personalized generation. Inspired by the application of collaborative filtering in recommender systems, we propose a method called CFRAG, which adapts Collaborative Filtering to RAG for personalized text generation. However, this presents two challenges: (1)~how to incorporate collaborative information without explicit user similarity labels? (2)~how to retrieve documents that support personalized LLM generation? For Challenge 1, we use contrastive learning to train user embeddings to retrieve similar users and introduce collaborative information. For Challenge 2, we design a personalized retriever and reranker to retrieve the top-$k$ documents from these users' histories. We take into account the user's preference during retrieval and reranking. Then we leverage feedback from the LLM to fine-tune the personalized retriever and reranker, enabling them to retrieve documents that meet the personalized generation needs of the LLM. Experimental results on the Language Model Personalization (LaMP) benchmark validate the effectiveness of CFRAG. Further analysis confirms the importance of incorporating collaborative information.
Composed Image Retrieval (CIR) aims to search an image of interest using a combination of a reference image and modification text as the query. Despite recent advancements, this task remains challenging due to limited training data and laborious triplet annotation processes. To address this issue, this paper proposes to synthesize the training triplets to augment the training resource for the CIR problem. Specifically, we commence by training a modification text generator exploiting large-scale multimodal models and scale up the CIR learning throughout both the pretraining and fine-tuning stages. During pretraining, we leverage the trained generator to directly create Modification Text-oriented Synthetic Triplets(MTST) conditioned on pairs of images. For fine-tuning, we first synthesize reverse modification text to connect the target image back to the reference image. Subsequently, we devise a two-hop alignment strategy to incrementally close the semantic gap between the multimodal pair and the target image. We initially learn an implicit prototype utilizing both the original triplet and its reversed version in a cycle manner, followed by combining the implicit prototype feature with the modification text to facilitate accurate alignment with the target image. Extensive experiments validate the efficacy of the generated triplets and confirm that our proposed methodology attains competitive recall on both the CIRR and FashionIQ benchmarks.
Recent progress in VLMs has demonstrated impressive capabilities across a variety of tasks in the natural image domain. Motivated by these advancements, the remote sensing community has begun to adopt VLMs for remote sensing vision-language tasks, including scene understanding, image captioning, and visual question answering. However, existing remote sensing VLMs typically rely on closed-set scene understanding and focus on generic scene descriptions, yet lack the ability to incorporate external knowledge. This limitation hinders their capacity for semantic reasoning over complex or context-dependent queries that involve domain-specific or world knowledge. To address these challenges, we first introduced a multimodal Remote Sensing World Knowledge (RSWK) dataset, which comprises high-resolution satellite imagery and detailed textual descriptions for 14,141 well-known landmarks from 175 countries, integrating both remote sensing domain knowledge and broader world knowledge. Building upon this dataset, we proposed a novel Remote Sensing Retrieval-Augmented Generation (RS-RAG) framework, which consists of two key components. The Multi-Modal Knowledge Vector Database Construction module encodes remote sensing imagery and associated textual knowledge into a unified vector space. The Knowledge Retrieval and Response Generation module retrieves and re-ranks relevant knowledge based on image and/or text queries, and incorporates the retrieved content into a knowledge-augmented prompt to guide the VLM in producing contextually grounded responses. We validated the effectiveness of our approach on three representative vision-language tasks, including image captioning, image classification, and visual question answering, where RS-RAG significantly outperformed state-of-the-art baselines.
Visual Question Answering (VQA) focuses on providing answers to natural language questions by utilizing information from images. Although cutting-edge multimodal large language models (MLLMs) such as GPT-4o achieve strong performance on VQA tasks, they frequently fall short in accessing domain-specific or the latest knowledge. To mitigate this issue, retrieval-augmented generation (RAG) leveraging external knowledge bases (KBs), referred to as KB-VQA, emerges as a promising approach. Nevertheless, conventional unimodal retrieval techniques, which translate images into textual descriptions, often result in the loss of critical visual details. This study presents fine-grained knowledge units, which merge textual snippets with entity images stored in vector databases. Furthermore, we introduce a knowledge unit retrieval-augmented generation framework (KU-RAG) that integrates fine-grained retrieval with MLLMs. The proposed KU-RAG framework ensures precise retrieval of relevant knowledge and enhances reasoning capabilities through a knowledge correction chain. Experimental findings demonstrate that our approach significantly boosts the performance of leading KB-VQA methods, achieving improvements of up to 10%.