Few-shot cross-modal retrieval focuses on learning cross-modal representations with limited training samples, enabling the model to handle unseen classes during inference. Unlike traditional cross-modal retrieval tasks, which assume that both training and testing data share the same class distribution, few-shot retrieval involves data with sparse representations across modalities. Existing methods often fail to adequately model the multi-peak distribution of few-shot cross-modal data, resulting in two main biases in the latent semantic space: intra-modal bias, where sparse samples fail to capture intra-class diversity, and inter-modal bias, where misalignments between image and text distributions exacerbate the semantic gap. These biases hinder retrieval accuracy. To address these issues, we propose a novel method, GCRDP, for few-shot cross-modal retrieval. This approach effectively captures the complex multi-peak distribution of data using a Gaussian Mixture Model (GMM) and incorporates a multi-positive sample contrastive learning mechanism for comprehensive feature modeling. Additionally, we introduce a new strategy for cross-modal semantic alignment, which constrains the relative distances between image and text feature distributions, thereby improving the accuracy of cross-modal representations. We validate our approach through extensive experiments on four benchmark datasets, demonstrating superior performance over six state-of-the-art methods.
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. Existing LLMs-based KGQA methods typically follow the Graph Retrieval-Augmented Generation (GraphRAG) paradigm, which first retrieves reasoning paths from the large KGs, and then generates the answers based on them. However, these methods emphasize the exploration of new optimal reasoning paths in KGs while ignoring the exploitation of historical reasoning paths, which may lead to sub-optimal reasoning paths. Additionally, the complex semantics contained in questions may lead to the retrieval of inaccurate reasoning paths. To address these issues, this paper proposes a novel and training-free framework for KGQA tasks called Reward-guided Tree Search on Graph (RTSoG). RTSoG decomposes an original question into a series of simpler and well-defined sub-questions to handle the complex semantics. Then, a Self-Critic Monte Carlo Tree Search (SC-MCTS) guided by a reward model is introduced to iteratively retrieve weighted reasoning paths as contextual knowledge. Finally, it stacks the weighted reasoning paths according to their weights to generate the final answers. Extensive experiments on four datasets demonstrate the effectiveness of RTSoG. Notably, it achieves 8.7\% and 7.0\% performance improvement over the state-of-the-art method on the GrailQA and the WebQSP respectively.
Large Language Models (LLMs)-based hybrid retrieval uses LLMs to encode queries and documents into low-dimensional dense or high-dimensional sparse vectors. It retrieves documents relevant to search queries based on vector similarities. Documents are pre-encoded offline, while queries arrive in real-time, necessitating an efficient online query encoder. Although LLMs significantly enhance retrieval capabilities, serving deeply parameterized LLMs slows down query inference throughput and increases demands for online deployment resources. In this paper, we propose LightRetriever, a novel LLM-based hybrid retriever with extremely lightweight query encoders. Our method retains a full-sized LLM for document encoding, but reduces the workload of query encoding to no more than an embedding lookup. Compared to serving a full-sized LLM on an H800 GPU, our approach achieves over a 1000x speedup for query inference with GPU acceleration, and even a 20x speedup without GPU. Experiments on large-scale retrieval benchmarks demonstrate that our method generalizes well across diverse retrieval tasks, retaining an average of 95% full-sized performance.
Large Language Model (LLM)-based search agents have shown remarkable capabilities in solving complex tasks by dynamically decomposing problems and addressing them through interleaved reasoning and retrieval. However, this interleaved paradigm introduces substantial efficiency bottlenecks. First, we observe that both highly accurate and overly approximate retrieval methods degrade system efficiency: exact search incurs significant retrieval overhead, while coarse retrieval requires additional reasoning steps during generation. Second, we identify inefficiencies in system design, including improper scheduling and frequent retrieval stalls, which lead to cascading latency -- where even minor delays in retrieval amplify end-to-end inference time. To address these challenges, we introduce SearchAgent-X, a high-efficiency inference framework for LLM-based search agents. SearchAgent-X leverages high-recall approximate retrieval and incorporates two key techniques: priority-aware scheduling and non-stall retrieval. Extensive experiments demonstrate that SearchAgent-X consistently outperforms state-of-the-art systems such as vLLM and HNSW-based retrieval across diverse tasks, achieving up to 3.4$\times$ higher throughput and 5$\times$ lower latency, without compromising generation quality. SearchAgent-X is available at https://github.com/tiannuo-yang/SearchAgent-X.
Competitive programming benchmarks are widely used in scenarios such as programming contests and large language model assessments. However, the growing presence of duplicate or highly similar problems raises concerns not only about competition fairness, but also about the validity of competitive programming as a benchmark for model evaluation. In this paper, we propose a new problem -- similar question retrieval -- to address this issue. Due to the lack of both data and models, solving this problem is challenging. To this end, we introduce CPRet, a retrieval-oriented benchmark suite for competitive programming, covering four retrieval tasks: two code-centric (i.e., Text-to-Code and Code-to-Code) and two newly proposed problem-centric tasks (i.e., Problem-to-Duplicate and Simplified-to-Full), built from a combination of automatically crawled problem-solution data and manually curated annotations. Our contribution includes both high-quality training data and temporally separated test sets for reliable evaluation. In addition, we develop two task-specialized retrievers based on this dataset: CPRetriever-Code, trained with a novel Group-InfoNCE loss for problem-code alignment, and CPRetriever-Prob, fine-tuned for identifying problem-level similarity. Both models achieve strong results and are open-sourced for local use. Finally, we analyze LiveCodeBench and find that high-similarity problems inflate model pass rates and reduce differentiation, underscoring the need for similarity-aware evaluation in future benchmarks. Code and data are available at: https://github.com/coldchair/CPRet
Retrieval-augmented generation (RAG) has emerged as a pivotal method for expanding the knowledge of large language models. To handle complex queries more effectively, researchers developed Adaptive-RAG (A-RAG) to enhance the generated quality through multiple interactions with external knowledge bases. Despite its effectiveness, A-RAG exacerbates the pre-existing efficiency challenges inherent in RAG, which are attributable to its reliance on multiple iterations of generation. Existing A-RAG approaches process all retrieved contents from scratch. However, they ignore the situation where there is a significant overlap in the content of the retrieval results across rounds. The overlapping content is redundantly represented, which leads to a large proportion of repeated computations, thus affecting the overall efficiency. To address this issue, this paper introduces a model-agnostic approach that can be generally applied to A-RAG methods, which is dedicated to reducing the redundant representation process caused by the overlapping of retrieval results. Specifically, we use cache access and parallel generation to speed up the prefilling and decoding stages respectively. Additionally, we also propose an instruction-driven module to further guide the model to more effectively attend to each part of the content in a more suitable way for LLMs. Experiments show that our approach achieves 2.79 and 2.33 times significant acceleration on average for prefilling and decoding respectively while maintaining equal generation quality.
Recent advances in large language models (LLMs) have led to impressive progress in natural language generation, yet their tendency to produce hallucinated or unsubstantiated content remains a critical concern. To improve factual reliability, Retrieval-Augmented Generation (RAG) integrates external knowledge during inference. However, existing RAG systems face two major limitations: (1) unreliable adaptive control due to limited external knowledge supervision, and (2) hallucinations caused by inaccurate or irrelevant references. To address these issues, we propose Know3-RAG, a knowledge-aware RAG framework that leverages structured knowledge from knowledge graphs (KGs) to guide three core stages of the RAG process, including retrieval, generation, and filtering. Specifically, we introduce a knowledge-aware adaptive retrieval module that employs KG embedding to assess the confidence of the generated answer and determine retrieval necessity, a knowledge-enhanced reference generation strategy that enriches queries with KG-derived entities to improve generated reference relevance, and a knowledge-driven reference filtering mechanism that ensures semantic alignment and factual accuracy of references. Experiments on multiple open-domain QA benchmarks demonstrate that Know3-RAG consistently outperforms strong baselines, significantly reducing hallucinations and enhancing answer reliability.
Large language models (LLMs) have been widely deployed with rapidly expanding context windows to support increasingly demanding applications. However, long contexts pose significant deployment challenges, primarily due to the KV cache whose size grows proportionally with context length. While KV cache compression methods are proposed to address this issue, KV dropping methods incur considerable accuracy loss, and KV retrieval methods suffer from significant efficiency bottlenecks. We propose FreeKV, an algorithm-system co-optimization framework to enhance KV retrieval efficiency while preserving accuracy. On the algorithm side, FreeKV introduces speculative retrieval to shift the KV selection and recall processes out of the critical path, combined with fine-grained correction to ensure accuracy. On the system side, FreeKV employs hybrid KV layouts across CPU and GPU memory to eliminate fragmented data transfers, and leverages double-buffered streamed recall to further improve efficiency. Experiments demonstrate that FreeKV achieves near-lossless accuracy across various scenarios and models, delivering up to 13$\times$ speedup compared to SOTA KV retrieval methods.
Large language models (LLMs) have advanced the field of artificial intelligence (AI) and are a powerful enabler for interactive systems. However, they still face challenges in long-term interactions that require adaptation towards the user as well as contextual knowledge and understanding of the ever-changing environment. To overcome these challenges, holistic memory modeling is required to efficiently retrieve and store relevant information across interaction sessions for suitable responses. Cognitive AI, which aims to simulate the human thought process in a computerized model, highlights interesting aspects, such as thoughts, memory mechanisms, and decision-making, that can contribute towards improved memory modeling for LLMs. Inspired by these cognitive AI principles, we propose our memory framework CAIM. CAIM consists of three modules: 1.) The Memory Controller as the central decision unit; 2.) the Memory Retrieval, which filters relevant data for interaction upon request; and 3.) the Post-Thinking, which maintains the memory storage. We compare CAIM against existing approaches, focusing on metrics such as retrieval accuracy, response correctness, contextual coherence, and memory storage. The results demonstrate that CAIM outperforms baseline frameworks across different metrics, highlighting its context-awareness and potential to improve long-term human-AI interactions.
The rise of time-series pre-trained models has advanced temporal representation learning, but current state-of-the-art models are often large-scale, requiring substantial compute. We introduce TSPulse, ultra-compact time-series pre-trained models with only 1M parameters, specialized to perform strongly across classification, anomaly detection, imputation, and retrieval tasks. TSPulse introduces innovations at both the architecture and task levels. At the architecture level, it employs a dual-space masked reconstruction, learning from both time and frequency domains to capture complementary signals. This is further enhanced by a dual-embedding disentanglement, generating both detailed embeddings for fine-grained analysis and high-level semantic embeddings for broader task understanding. Notably, TSPulse's semantic embeddings are robust to shifts in time, magnitude, and noise, which is important for robust retrieval. At the task level, TSPulse incorporates TSLens, a fine-tuning component enabling task-specific feature attention. It also introduces a multi-head triangulation technique that correlates deviations from multiple prediction heads, enhancing anomaly detection by fusing complementary model outputs. Additionally, a hybrid mask pretraining is proposed to improves zero-shot imputation by reducing pre-training bias. These architecture and task innovations collectively contribute to TSPulse's significant performance gains: 5-16% on the UEA classification benchmarks, +20% on the TSB-AD anomaly detection leaderboard, +50% in zero-shot imputation, and +25% in time-series retrieval. Remarkably, these results are achieved with just 1M parameters, making TSPulse 10-100X smaller than existing pre-trained models. Its efficiency enables GPU-free inference and rapid pre-training, setting a new standard for efficient time-series pre-trained models. Models will be open-sourced soon.
While large language models (LLMs) have demonstrated strong capabilities in tasks like question answering and fact verification, they continue to suffer from hallucinations and reasoning errors, especially in multi-hop tasks that require integration of multiple information sources. Current methods address these issues through retrieval-based techniques (grounding reasoning in external evidence), reasoning-based approaches (enhancing coherence via improved prompting), or hybrid strategies combining both elements. One prominent hybrid method, ReAct, has outperformed purely retrieval-based or reasoning-based approaches; however, it lacks internal verification of intermediate reasoning steps, allowing potential errors to propagate through complex reasoning tasks. In this paper, we introduce Reasoning Court (RC), a novel framework that extends iterative reasoning-and-retrieval methods, such as ReAct, with a dedicated LLM judge. Unlike ReAct, RC employs this judge to independently evaluate multiple candidate answers and their associated reasoning generated by separate LLM agents. The judge is asked to select the answer that it considers the most factually grounded and logically coherent based on the presented reasoning and evidence, or synthesizes a new answer using available evidence and its pre-trained knowledge if all candidates are inadequate, flawed, or invalid. Evaluations on multi-hop benchmarks (HotpotQA, MuSiQue) and fact-verification (FEVER) demonstrate that RC consistently outperforms state-of-the-art few-shot prompting methods without task-specific fine-tuning.
Large language models have demonstrated impressive reasoning capabilities but are inherently limited by their knowledge reservoir. Retrieval-augmented reasoning mitigates this limitation by allowing LLMs to query external resources, but existing methods often retrieve irrelevant or noisy information, hindering accurate reasoning. In this paper, we propose AutoRefine, a reinforcement learning post-training framework that adopts a new ``search-and-refine-during-think'' paradigm. AutoRefine introduces explicit knowledge refinement steps between successive search calls, enabling the model to iteratively filter, distill, and organize evidence before generating an answer. Furthermore, we incorporate tailored retrieval-specific rewards alongside answer correctness rewards using group relative policy optimization. Experiments on single-hop and multi-hop QA benchmarks demonstrate that AutoRefine significantly outperforms existing approaches, particularly in complex, multi-hop reasoning scenarios. Detailed analysis shows that AutoRefine issues frequent, higher-quality searches and synthesizes evidence effectively.
This study investigates the challenges of translating low-resource languages by integrating Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG). Various model configurations were tested on Hakka translations, with BLEU scores ranging from 12% (dictionary-only) to 31% (RAG with Gemini 2.0). The best-performing model (Model 4) combined retrieval and advanced language modeling, improving lexical coverage, particularly for specialized or culturally nuanced terms, and enhancing grammatical coherence. A two-stage method (Model 3) using dictionary outputs refined by Gemini 2.0 achieved a BLEU score of 26%, highlighting iterative correction's value and the challenges of domain-specific expressions. Static dictionary-based approaches struggled with context-sensitive content, demonstrating the limitations of relying solely on predefined resources. These results emphasize the need for curated resources, domain knowledge, and ethical collaboration with local communities, offering a framework that improves translation accuracy and fluency while supporting cultural preservation.
Graph-based retrieval-augmented generation (RAG) enables large language models (LLMs) to incorporate structured knowledge via graph retrieval as contextual input, enhancing more accurate and context-aware reasoning. We observe that for different queries, it could retrieve similar subgraphs as prompts, and thus we propose SubGCache, which aims to reduce inference latency by reusing computation across queries with similar structural prompts (i.e., subgraphs). Specifically, SubGCache clusters queries based on subgraph embeddings, constructs a representative subgraph for each cluster, and pre-computes the key-value (KV) cache of the representative subgraph. For each query with its retrieved subgraph within a cluster, it reuses the pre-computed KV cache of the representative subgraph of the cluster without computing the KV tensors again for saving computation. Experiments on two new datasets across multiple LLM backbones and graph-based RAG frameworks demonstrate that SubGCache consistently reduces inference latency with comparable and even improved generation quality, achieving up to 6.68$\times$ reduction in time-to-first-token (TTFT).
Multi-vector models, such as ColBERT, are a significant advancement in neural information retrieval (IR), delivering state-of-the-art performance by representing queries and documents by multiple contextualized token-level embeddings. However, this increased representation size introduces considerable storage and computational overheads which have hindered widespread adoption in practice. A common approach to mitigate this overhead is to cluster the model's frozen vectors, but this strategy's effectiveness is fundamentally limited by the intrinsic clusterability of these embeddings. In this work, we introduce CRISP (Clustered Representations with Intrinsic Structure Pruning), a novel multi-vector training method which learns inherently clusterable representations directly within the end-to-end training process. By integrating clustering into the training phase rather than imposing it post-hoc, CRISP significantly outperforms post-hoc clustering at all representation sizes, as well as other token pruning methods. On the BEIR retrieval benchmarks, CRISP achieves a significant rate of ~3x reduction in the number of vectors while outperforming the original unpruned model. This indicates that learned clustering effectively denoises the model by filtering irrelevant information, thereby generating more robust multi-vector representations. With more aggressive clustering, CRISP achieves an 11x reduction in the number of vectors with only a $3.6\%$ quality loss.
Industry-scale recommender systems face a core challenge: representing entities with high cardinality, such as users or items, using dense embeddings that must be accessible during both training and inference. However, as embedding sizes grow, memory constraints make storage and access increasingly difficult. We describe a lightweight, learnable embedding compression technique that projects dense embeddings into a high-dimensional, sparsely activated space. Designed for retrieval tasks, our method reduces memory requirements while preserving retrieval performance, enabling scalable deployment under strict resource constraints. Our results demonstrate that leveraging sparsity is a promising approach for improving the efficiency of large-scale recommenders. We release our code at https://github.com/recombee/CompresSAE.
Large Language Models (LLMs) are increasingly deployed across edge and cloud platforms for real-time question-answering and retrieval-augmented generation. However, processing lengthy contexts in distributed systems incurs high computational overhead, memory usage, and network bandwidth. This paper introduces a novel semantic caching approach for storing and reusing intermediate contextual summaries, enabling efficient information reuse across similar queries in LLM-based QA workflows. Our method reduces redundant computations by up to 50-60% while maintaining answer accuracy comparable to full document processing, as demonstrated on NaturalQuestions, TriviaQA, and a synthetic ArXiv dataset. This approach balances computational cost and response quality, critical for real-time AI assistants.
Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for enhancing the capabilities of large language models. However, existing RAG evaluation predominantly focuses on text retrieval and relies on opaque, end-to-end assessments of generated outputs. To address these limitations, we introduce mmRAG, a modular benchmark designed for evaluating multi-modal RAG systems. Our benchmark integrates queries from six diverse question-answering datasets spanning text, tables, and knowledge graphs, which we uniformly convert into retrievable documents. To enable direct, granular evaluation of individual RAG components -- such as the accuracy of retrieval and query routing -- beyond end-to-end generation quality, we follow standard information retrieval procedures to annotate document relevance and derive dataset relevance. We establish baseline performance by evaluating a wide range of RAG implementations on mmRAG.
This paper systematically addresses the challenges of rule retrieval, a crucial yet underexplored area. Vanilla retrieval methods using sparse or dense retrievers to directly search for relevant rules to support downstream reasoning, often suffer from low accuracy. This is primarily due to a significant semantic gap between the instantiated facts in the queries and the abstract representations of the rules. Such misalignment results in suboptimal retrieval quality, which in turn negatively impacts reasoning performance. To overcome these challenges, we propose Self-Induction Augmented Retrieval (SIAR), a novel approach that utilizes Large Language Models (LLMs) to induce potential inferential rules that might offer benefits for reasoning by abstracting the underlying knowledge and logical structure in queries. These induced rules are then used for query augmentation to improve retrieval effectiveness. Additionally, we introduce Rule Relevance ReEstimate (R$^3$), a method that re-estimates the relevance of retrieved rules by assessing whether the abstract knowledge they contain can be instantiated to align with the facts in the queries and the helpfulness for reasoning. Extensive experiments across various settings demonstrate the effectiveness and versatility of our proposed methods.
The rapid spread of online disinformation presents a global challenge, and machine learning has been widely explored as a potential solution. However, multilingual settings and low-resource languages are often neglected in this field. To address this gap, we conducted a shared task on multilingual claim retrieval at SemEval 2025, aimed at identifying fact-checked claims that match newly encountered claims expressed in social media posts across different languages. The task includes two subtracks: (1) a monolingual track, where social posts and claims are in the same language, and (2) a crosslingual track, where social posts and claims might be in different languages. A total of 179 participants registered for the task contributing to 52 test submissions. 23 out of 31 teams have submitted their system papers. In this paper, we report the best-performing systems as well as the most common and the most effective approaches across both subtracks. This shared task, along with its dataset and participating systems, provides valuable insights into multilingual claim retrieval and automated fact-checking, supporting future research in this field.