Retrieval-Augmented Generation (RAG) has emerged as a promising approach for knowledge-intensive tasks. However, few studies have examined RAG for Taiwanese Historical Archives. In this paper, we present an initial study of a RAG pipeline applied to two historical Traditional Chinese datasets, Fort Zeelandia and the Taiwan Provincial Council Gazette, along with their corresponding open-ended query sets. We systematically investigate the effects of query characteristics and metadata integration strategies on retrieval quality, answer generation, and the performance of the overall system. The results show that early-stage metadata integration enhances both retrieval and answer accuracy while also revealing persistent challenges for RAG systems, including hallucinations during generation and difficulties in handling temporal or multi-hop historical queries.

The integration of AI tools into medical applications has aimed to improve the efficiency of diagnosis. The emergence of large language models (LLMs), such as ChatGPT and Claude, has expanded this integration even further. Because of LLM versatility and ease of use through APIs, these larger models are often utilised even though smaller, custom models can be used instead. In this paper, LLMs and small discriminative models are integrated into a Mendix application to detect Covid-19 in chest X-rays. These discriminative models are also used to provide knowledge bases for LLMs to improve accuracy. This provides a benchmark study of 14 different model configurations for comparison of accuracy and environmental impact. The findings indicated that while smaller models reduced the carbon footprint of the application, the output was biased towards a positive diagnosis and the output probabilities were lacking confidence. Meanwhile, restricting LLMs to only give probabilistic output caused poor performance in both accuracy and carbon footprint, demonstrating the risk of using LLMs as a universal AI solution. While using the smaller LLM GPT-4.1-Nano reduced the carbon footprint by 94.2% compared to the larger models, this was still disproportionate to the discriminative models; the most efficient solution was the Covid-Net model. Although it had a larger carbon footprint than other small models, its carbon footprint was 99.9% less than when using GPT-4.5-Preview, whilst achieving an accuracy of 95.5%, the highest of all models examined. This paper contributes to knowledge by comparing generative and discriminative models in Covid-19 detection as well as highlighting the environmental risk of using generative tools for classification tasks.

As the demand for human-like reasoning, multi-turn dialogues, and long-form responses grows, large language models (LLMs) are increasingly expected to support efficient and effective long-sequence decoding. However, due to limited DRAM capacity, long-seuqence LLM decoding on smartphones is constrained by the key-value cache (KVCache), whose memory footprint increases linearly with sequence length. Retrieval-based methods mitigate DRAM pressure by offloading KVCache to flash and retrieving query-relevant entries through cluster-based indexing. Unfortunately, as decoding progresses, KVCache distribution shifts render static or local cluster updates progressively misaligned, excluding essential entries or fetching redundant ones. These issues are further exacerbated by smartphone-specific limitations in bandwidth, IOPS, and memory capacity. We propose DynaKV, the first adaptive KVCache management approach that jointly addresses accuracy and efficiency for long-sequence decoding on smartphones. DynaKV integrates three key techniques: (1) Migration-Free Cluster Adaptation, which adaptively splits clusters during retrieval without incurring additional transfers; (2) Continuity-Centric Flash Management, which co-locates correlated entries and clusters and employs a dual-head layout for efficient updates; and (3) Memory-Efficient Cache Design, which virtualizes cache space across DRAM and flash and extends replacement policies to align with cluster-level access patterns. Evaluations demonstrate that DynaKV improves retrieval accuracy and reduces end-to-end latency compared to state-of-the-art solutions, achieving average gains of $1.38\times$ in accuracy and $1.47\times$ speedups. Furthermore, the insights of DynaKV naturally extend to other long-context workloads and multi-tier memory hierarchies, underscoring its broader applicability.

Model Context Protocol (MCP) has recently gained increased attention within the AI community for providing a standardized way for large language models (LLMs) to interact with external tools and services, significantly enhancing their capabilities. However, the inclusion of extensive contextual information, including system prompts, MCP tool definitions, and context histories, in MCP-enabled LLM interactions, dramatically inflates token usage. Given that LLM providers charge based on tokens, these expanded contexts can quickly escalate monetary costs and increase the computational load on LLM services. This paper presents a comprehensive measurement-based analysis of MCP-enabled interactions with LLMs, revealing trade-offs between capability, performance, and cost. We explore how different LLM models and MCP configurations impact key performance metrics such as token efficiency, monetary cost, task completion times, and task success rates, and suggest potential optimizations, including enabling parallel tool calls and implementing robust task abort mechanisms. These findings provide useful insights for developing more efficient, robust, and cost-effective MCP-enabled workflows.

The growing demand for on-device large language model (LLM) inference is driving interest in deploying lightweight, cost-effective AI solutions on edge hardware. Single-board computers (SBCs) such as the Raspberry Pi and Orange Pi offer a promising platform for localized, privacy-preserving inference-but remain underexplored in the context of LLM workloads. In this work, we benchmark the performance of 25 quantized open-source LLMs across three SBCs-Raspberry Pi 4, Raspberry Pi 5, and Orange Pi 5 Pro-using two inference runtimes: Ollama and Llamafile. We evaluate generation throughput, memory usage, and power consumption under varying CPU configurations, using multiple prompt types to simulate realistic workloads. Our results show that SBCs can reliably support models up to 1.5B parameters, with Llamafile achieving up to 4x higher throughput and 30-40% lower power usage than Ollama. We identify architecture-specific bottlenecks, highlight runtime-level trade-offs, and provide practical deployment recommendations. This study offers the first broad evaluation of LLM inference on SBCs, bridging the gap between high-performance language models and affordable edge computing.

Large Language Models (LLMs) are becoming key components in various mobile operating systems, driving smart applications like interactive chatbots and personal assistants. While bringing enhanced intelligence to mobile ends, their deployment suffers from a set of performance challenges, especially the generation quality degradation and prolonged latency. Prior works have mainly relied on solutions of cloud offloading or on-device Small Language Models (SLMs). However, the former is usually limited by the communication bottleneck, and the latter sacrifices generation quality due to resource constraints. To mitigate these limitations, this paper proposes Synera, a device-cloud synergistic LLM serving system that applies an efficient SLM-LLM synergistic mechanism. Through empirical studies on LLM's unique computing characteristics, Synera identifies a set of underexplored optimization opportunities in device-cloud synergistic LLM inference, including offloading decisions, pipeline stalls, and batching bottlenecks. To translate them into enhanced performance, Synera introduces tailored designs of communication-efficient selective offloading, stall-free parallel inference, and scalable cloud batching. Extensive evaluations with real-world testbeds show that Synera enables 1.20-5.47x better generation quality against competitive baselines with on-par latency performance. Compared with existing cloud serving, Synera achieves 8.2-16.5% lower cloud serving cost on various benchmarks.

While LLMs have shown great success in financial tasks like stock prediction and question answering, their application in fully automating Equity Research Report generation remains uncharted territory. In this paper, we formulate the Equity Research Report (ERR) Generation task for the first time. To address the data scarcity and the evaluation metrics absence, we present an open-source evaluation benchmark for ERR generation - FinRpt. We frame a Dataset Construction Pipeline that integrates 7 financial data types and produces a high-quality ERR dataset automatically, which could be used for model training and evaluation. We also introduce a comprehensive evaluation system including 11 metrics to assess the generated ERRs. Moreover, we propose a multi-agent framework specifically tailored to address this task, named FinRpt-Gen, and train several LLM-based agents on the proposed datasets using Supervised Fine-Tuning and Reinforcement Learning. Experimental results indicate the data quality and metrics effectiveness of the benchmark FinRpt and the strong performance of FinRpt-Gen, showcasing their potential to drive innovation in the ERR generation field. All code and datasets are publicly available.

Implicit feedback, employed in training recommender systems, unavoidably confronts noise due to factors such as misclicks and position bias. Previous studies have attempted to identify noisy samples through their diverged data patterns, such as higher loss values, and mitigate their influence through sample dropping or reweighting. However, we observed that noisy samples and hard samples display similar patterns, leading to hard-noisy confusion issue. Such confusion is problematic as hard samples are vital for modeling user preferences. To solve this problem, we propose LLMHNI framework, leveraging two auxiliary user-item relevance signals generated by Large Language Models (LLMs) to differentiate hard and noisy samples. LLMHNI obtains user-item semantic relevance from LLM-encoded embeddings, which is used in negative sampling to select hard negatives while filtering out noisy false negatives. An objective alignment strategy is proposed to project LLM-encoded embeddings, originally for general language tasks, into a representation space optimized for user-item relevance modeling. LLMHNI also exploits LLM-inferred logical relevance within user-item interactions to identify hard and noisy samples. These LLM-inferred interactions are integrated into the interaction graph and guide denoising with cross-graph contrastive alignment. To eliminate the impact of unreliable interactions induced by LLM hallucination, we propose a graph contrastive learning strategy that aligns representations from randomly edge-dropped views to suppress unreliable edges. Empirical results demonstrate that LLMHNI significantly improves denoising and recommendation performance.

Large language models sometimes inadvertently reproduce passages that are copyrighted, exposing downstream applications to legal risk. Most existing studies for inference-time defences focus on surface-level token matching and rely on external blocklists or filters, which add deployment complexity and may overlook semantically paraphrased leakage. In this work, we reframe copyright infringement mitigation as intrinsic semantic-space control and introduce SCOPE, an inference-time method that requires no parameter updates or auxiliary filters. Specifically, the sparse autoencoder (SAE) projects hidden states into a high-dimensional, near-monosemantic space; benefiting from this representation, we identify a copyright-sensitive subspace and clamp its activations during decoding. Experiments on widely recognized benchmarks show that SCOPE mitigates copyright infringement without degrading general utility. Further interpretability analyses confirm that the isolated subspace captures high-level semantics.

The rapid advancement of Large Language Models (LLMs) has driven significant progress in Natural Language Interface to Database (NLIDB). However, the widespread adoption of LLMs has raised critical privacy and security concerns. During interactions, LLMs may unintentionally expose confidential database contents or be manipulated by attackers to exfiltrate data through seemingly benign queries. While current efforts typically rely on rule-based heuristics or LLM agents to mitigate this leakage risk, these methods still struggle with complex inference-based attacks, suffer from high false positive rates, and often compromise the reliability of SQL queries. To address these challenges, we propose \textsc{SafeNlidb}, a novel privacy-security alignment framework for LLM-based NLIDB. The framework features an automated pipeline that generates hybrid chain-of-thought interaction data from scratch, seamlessly combining implicit security reasoning with SQL generation. Additionally, we introduce reasoning warm-up and alternating preference optimization to overcome the multi-preference oscillations of Direct Preference Optimization (DPO), enabling LLMs to produce security-aware SQL through fine-grained reasoning without the need for human-annotated preference data. Extensive experiments demonstrate that our method outperforms both larger-scale LLMs and ideal-setting baselines, achieving significant security improvements while preserving high utility. WARNING: This work may contain content that is offensive and harmful!