This paper introduces SLOs-Serve, a system designed for serving multi-stage large language model (LLM) requests with application- and stage-specific service level objectives (SLOs). The key idea behind SLOs-Serve is to customize the allocation of tokens to meet these SLO requirements. SLOs-Serve uses a multi-SLO dynamic programming-based algorithm to continuously optimize token allocations under SLO constraints by exploring the full design space of chunked prefill and (optional) speculative decoding. Leveraging this resource planning algorithm, SLOs-Serve effectively supports multi-SLOs and multi-replica serving with dynamic request routing while being resilient to bursty arrivals. Our evaluation across 6 LLM application scenarios (including summarization, coding, chatbot, tool calling, and reasoning) demonstrates that SLOs-Serve improves per-GPU serving capacity by 2.2x on average compared to prior state-of-the-art systems.
Language model deployments in consumer-facing applications introduce numerous risks. While existing research on harms and hazards of such applications follows top-down approaches derived from regulatory frameworks and theoretical analyses, empirical evidence of real-world failure modes remains underexplored. In this work, we introduce RealHarm, a dataset of annotated problematic interactions with AI agents built from a systematic review of publicly reported incidents. Analyzing harms, causes, and hazards specifically from the deployer's perspective, we find that reputational damage constitutes the predominant organizational harm, while misinformation emerges as the most common hazard category. We empirically evaluate state-of-the-art guardrails and content moderation systems to probe whether such systems would have prevented the incidents, revealing a significant gap in the protection of AI applications.
Circuit link prediction identifying missing component connections from incomplete netlists is crucial in automating analog circuit design. However, existing methods face three main challenges: 1) Insufficient use of topological patterns in circuit graphs reduces prediction accuracy; 2) Data scarcity due to the complexity of annotations hinders model generalization; 3) Limited adaptability to various netlist formats. We propose GNN-ACLP, a Graph Neural Networks (GNNs) based framework featuring three innovations to tackle these challenges. First, we introduce the SEAL (Subgraphs, Embeddings, and Attributes for Link Prediction) framework and achieve port-level accuracy in circuit link prediction. Second, we propose Netlist Babel Fish, a netlist format conversion tool leveraging retrieval-augmented generation (RAG) with a large language model (LLM) to enhance the compatibility of netlist formats. Finally, we construct SpiceNetlist, a comprehensive dataset that contains 775 annotated circuits across 10 different component classes. Experimental results achieve accuracy improvements of 16.08% on SpiceNetlist, 11.38% on Image2Net, and 16.01% on Masala-CHAI in intra-dataset evaluation, while maintaining accuracy from 92.05% to 99.07% in cross-dataset evaluation, exhibiting robust feature transfer capabilities.
Large Language Models (LLMs) have emerged as a powerful approach for driving offensive penetration-testing tooling. Due to the opaque nature of LLMs, empirical methods are typically used to analyze their efficacy. The quality of this analysis is highly dependent on the chosen testbed, captured metrics and analysis methods employed. This paper analyzes the methodology and benchmarking practices used for evaluating Large Language Model (LLM)-driven attacks, focusing on offensive uses of LLMs in cybersecurity. We review 19 research papers detailing 18 prototypes and their respective testbeds. We detail our findings and provide actionable recommendations for future research, emphasizing the importance of extending existing testbeds, creating baselines, and including comprehensive metrics and qualitative analysis. We also note the distinction between security research and practice, suggesting that CTF-based challenges may not fully represent real-world penetration testing scenarios.
Configuring computational fluid dynamics (CFD) simulations typically demands extensive domain expertise, limiting broader access. Although large language models (LLMs) have advanced scientific computing, their use in automating CFD workflows is underdeveloped. We introduce a novel approach centered on domain-specific LLM adaptation. By fine-tuning Qwen2.5-7B-Instruct on NL2FOAM, our custom dataset of 28716 natural language-to-OpenFOAM configuration pairs with chain-of-thought (CoT) annotations, we enable direct translation from natural language descriptions to executable CFD setups. A multi-agent framework orchestrates the process, autonomously verifying inputs, generating configurations, running simulations, and correcting errors. Evaluation on a benchmark of 21 diverse flow cases demonstrates state-of-the-art performance, achieving 88.7% solution accuracy and 82.6% first-attempt success rate. This significantly outperforms larger general-purpose models like Qwen2.5-72B-Instruct, DeepSeek-R1, and Llama3.3-70B-Instruct, while also requiring fewer correction iterations and maintaining high computational efficiency. The results highlight the critical role of domain-specific adaptation in deploying LLM assistants for complex engineering workflows. Our code and fine-tuned model have been deposited at https://github.com/YYgroup/AutoCFD.
Although LLM-based agents have attracted significant attention in domains such as software engineering and machine learning research, their role in advancing combinatorial optimization (CO) remains relatively underexplored. This gap underscores the need for a deeper understanding of their potential in tackling structured, constraint-intensive problems-a pursuit currently limited by the absence of comprehensive benchmarks for systematic investigation. To address this, we introduce CO-Bench, a benchmark suite featuring 36 real-world CO problems drawn from a broad range of domains and complexity levels. CO-Bench includes structured problem formulations and curated data to support rigorous investigation of LLM agents. We evaluate multiple agent frameworks against established human-designed algorithms, revealing key strengths and limitations of current approaches and identifying promising directions for future research. CO-Bench is publicly available at https://github.com/sunnweiwei/CO-Bench.
Time series analysis is crucial in fields like finance, transportation, and industry. However, traditional models often focus solely on temporal features, limiting their ability to capture underlying information. This paper proposes a novel time series multitask framework, called LTM, which integrates temporal features with textual descriptions to enhance analytical and predictive capabilities. LTM combines pre-trained time series model, large language model (LLM), and knowledge graph to tackle time series tasks, including forecasting, imputation, and anomaly detection. LTM achieves improved performance with a few trainable parameters. It is very efficient and practical. LTM encodes time series data into patches and enriches user-provided prompts using knowledge graphs to generate enhanced prompts. A novel feature fusion method embeds prompts into each patch encoding, which is processed by a frozen LLM, followed by a feature enhancement module and a time decoder module. During fine-tuning stage, cosine similarity between prompts and temporal patches is integrated into the loss function to boost performance. Experiments on benchmark datasets show that LTM significantly outperforms existing methods. It provides a robust and versatile solution for time series tasks.
We present a decoder-only Transformer architecture that robustly generalizes to sequence lengths substantially longer than those seen during training. Our model, SWAN-GPT, interleaves layers without positional encodings (NoPE) and sliding-window attention layers equipped with rotary positional encodings (SWA-RoPE). Experiments demonstrate strong performance on sequence lengths significantly longer than the training length without the need for additional long-context training. This robust length extrapolation is achieved through our novel architecture, enhanced by a straightforward dynamic scaling of attention scores during inference. In addition, SWAN-GPT is more computationally efficient than standard GPT architectures, resulting in cheaper training and higher throughput. Further, we demonstrate that existing pre-trained decoder-only models can be efficiently converted to the SWAN architecture with minimal continued training, enabling longer contexts. Overall, our work presents an effective approach for scaling language models to longer contexts in a robust and efficient manner.
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.
Heavy-duty trucks pose significant safety challenges due to their large size and limited maneuverability compared to passenger vehicles. A deeper understanding of truck characteristics is essential for enhancing the safety perspective of cooperative autonomous driving. Traditional LiDAR-based truck classification methods rely on extensive manual annotations, which makes them labor-intensive and costly. The rapid advancement of large language models (LLMs) trained on massive datasets presents an opportunity to leverage their few-shot learning capabilities for truck classification. However, existing vision-language models (VLMs) are primarily trained on image datasets, which makes it challenging to directly process point cloud data. This study introduces a novel framework that integrates roadside LiDAR point cloud data with VLMs to facilitate efficient and accurate truck classification, which supports cooperative and safe driving environments. This study introduces three key innovations: (1) leveraging real-world LiDAR datasets for model development, (2) designing a preprocessing pipeline to adapt point cloud data for VLM input, including point cloud registration for dense 3D rendering and mathematical morphological techniques to enhance feature representation, and (3) utilizing in-context learning with few-shot prompting to enable vehicle classification with minimally labeled training data. Experimental results demonstrate encouraging performance of this method and present its potential to reduce annotation efforts while improving classification accuracy.
Electronic health record (EHR) foundation models have been an area ripe for exploration with their improved performance in various medical tasks. Despite the rapid advances, there exists a fundamental limitation: Processing unseen medical codes out of the vocabulary. This problem limits the generality of EHR foundation models and the integration of models trained with different vocabularies. To deal with this problem, we propose MedRep for EHR foundation models based on the observational medical outcome partnership (OMOP) common data model (CDM), providing the integrated medical concept representations and the basic data augmentation strategy for patient trajectories. For concept representation learning, we enrich the information of each concept with a minimal definition through large language model (LLM) prompts and enhance the text-based representations through graph ontology of OMOP vocabulary. Trajectory augmentation randomly replaces selected concepts with other similar concepts that have closely related representations to let the model practice with the concepts out-of-vocabulary. Finally, we demonstrate that EHR foundation models trained with MedRep better maintain the prediction performance in external datasets. Our code implementation is publicly available at https://github.com/kicarussays/MedRep.
Advancements in emotion aware language processing increasingly shape vital NLP applications ranging from conversational AI and affective computing to computational psychology and creative content generation. Existing emotion datasets either lack emotional granularity or fail to capture necessary stylistic diversity, limiting the advancement of effective emotion conditioned text generation systems. Seeking to bridge this crucial gap between granularity and style diversity, this paper introduces a novel systematically constructed dataset named ELSA Emotion and Language Style Alignment Dataset leveraging fine grained emotion taxonomies adapted from existing sources such as dair ai emotion dataset and GoEmotions taxonomy. This dataset comprises multiple emotionally nuanced variations of original sentences regenerated across distinct contextual styles such as conversational, formal, poetic, and narrative, using advanced Large Language Models LLMs. Rigorous computational evaluation using metrics such as perplexity, embedding variance, readability, lexical diversity, and semantic coherence measures validates the datasets emotional authenticity, linguistic fluency, and textual diversity. Comprehensive metric analyses affirm its potential to support deeper explorations into emotion conditioned style adaptive text generation. By enabling precision tuned emotionally nuanced language modeling, our dataset creates fertile ground for research on fine grained emotional control, prompt driven explanation, interpretability, and style adaptive expressive language generation with LLMs.
Large language model (LLM)-driven AI systems may exhibit an inference failure mode we term `neural howlround,' a self-reinforcing cognitive loop where certain highly weighted inputs become dominant, leading to entrenched response patterns resistant to correction. This paper explores the mechanisms underlying this phenomenon, which is distinct from model collapse and biased salience weighting. We propose an attenuation-based correction mechanism that dynamically introduces counterbalancing adjustments and can restore adaptive reasoning, even in `locked-in' AI systems. Additionally, we discuss some other related effects arising from improperly managed reinforcement. Finally, we outline potential applications of this mitigation strategy for improving AI robustness in real-world decision-making tasks.
As the prevalence of mental health crises increases on social media platforms, identifying and preventing potential harm has become an urgent challenge. This study introduces a large language model (LLM)-based text transfer recognition method for social network crisis intervention, enhanced with domain-specific mental health knowledge. We propose a multi-level framework that incorporates transfer learning using BERT, and integrates mental health knowledge, sentiment analysis, and behavior prediction techniques. The framework includes a crisis annotation tool trained on social media datasets from real-world events, enabling the model to detect nuanced emotional cues and identify psychological crises. Experimental results show that the proposed method outperforms traditional models in crisis detection accuracy and exhibits greater sensitivity to subtle emotional and contextual variations.
We present AstroLLaVA, a vision language model for astronomy that enables interaction with astronomical imagery through natural dialogue. By fine-tuning the LLaVA model on a diverse dataset of $\sim$30k images with captions and question-answer pairs sourced from NASA's `Astronomy Picture of the Day', the European Southern Observatory, and the NASA/ESA Hubble Space Telescope, we create a model capable of answering open-ended questions about astronomical concepts depicted visually. Our two-stage fine-tuning process adapts the model to both image captioning and visual question answering in the astronomy domain. We demonstrate AstroLLaVA's performance on an astronomical visual question answering benchmark and release the model weights, code, and training set to encourage further open source work in this space. Finally, we suggest a roadmap towards general astronomical data alignment with pre-trained language models, and provide an open space for collaboration towards this end for interested researchers.
Source code comes in different shapes and forms. Previous research has already shown code to be more predictable than natural language as well as highlighted its statistical predictability at the token level: source code can be natural. More recently, the structure of code -- control flow, syntax graphs, abstract syntax trees etc. -- has been successfully used to improve the state-of-the-art on numerous tasks: code suggestion, code summarisation, method naming etc. This body of work implicitly assumes that structured representations of code are similarly statistically predictable, i.e. that a structured view of code is also natural. We consider that this view should be made explicit and propose directly studying the Structured Naturalness Hypothesis. Beyond just naming existing research that assumes this hypothesis and formulating it, we also provide evidence in the case of trees: TreeLSTM models over ASTs for some languages, such as Ruby, are competitive with $n$-gram models while handling the syntax token issue highlighted by previous research 'for free'. For other languages, such as Java or Python, we find tree models to perform worse, suggesting that downstream task improvement is uncorrelated to the language modelling task. Further, we show how such naturalness signals can be employed for near state-of-the-art results on just-in-time defect prediction while forgoing manual feature engineering work.
Vision models are increasingly deployed in critical applications such as autonomous driving and CCTV monitoring, yet they remain susceptible to resource-consuming attacks. In this paper, we introduce a novel energy-overloading attack that leverages vision language model (VLM) prompts to generate adversarial images targeting vision models. These images, though imperceptible to the human eye, significantly increase GPU energy consumption across various vision models, threatening the availability of these systems. Our framework, EO-VLM (Energy Overload via VLM), is model-agnostic, meaning it is not limited by the architecture or type of the target vision model. By exploiting the lack of safety filters in VLMs like DALL-E 3, we create adversarial noise images without requiring prior knowledge or internal structure of the target vision models. Our experiments demonstrate up to a 50% increase in energy consumption, revealing a critical vulnerability in current vision models.
We study $\textit{how}$ rich visual semantic information is represented within various layers and denoising timesteps of different diffusion architectures. We uncover monosemantic interpretable features by leveraging k-sparse autoencoders (k-SAE). We substantiate our mechanistic interpretations via transfer learning using light-weight classifiers on off-the-shelf diffusion models' features. On $4$ datasets, we demonstrate the effectiveness of diffusion features for representation learning. We provide in-depth analysis of how different diffusion architectures, pre-training datasets, and language model conditioning impacts visual representation granularity, inductive biases, and transfer learning capabilities. Our work is a critical step towards deepening interpretability of black-box diffusion models. Code and visualizations available at: https://github.com/revelio-diffusion/revelio
This study examines hallucinations in Large Language Model (LLM) translations into Irish, specifically focusing on instances where the models generate novel, non-existent words. We classify these hallucinations within verb and noun categories, identifying six distinct patterns among the latter. Additionally, we analyse whether these hallucinations adhere to Irish morphological rules and what linguistic tendencies they exhibit. Our findings show that while both GPT-4.o and GPT-4.o Mini produce similar types of hallucinations, the Mini model generates them at a significantly higher frequency. Beyond classification, the discussion raises speculative questions about the implications of these hallucinations for the Irish language. Rather than seeking definitive answers, we offer food for thought regarding the increasing use of LLMs and their potential role in shaping Irish vocabulary and linguistic evolution. We aim to prompt discussion on how such technologies might influence language over time, particularly in the context of low-resource, morphologically rich languages.
We propose a novel framework for generating causal graphs from narrative texts, bridging high-level causality and detailed event-specific relationships. Our method first extracts concise, agent-centered vertices using large language model (LLM)-based summarization. We introduce an "Expert Index," comprising seven linguistically informed features, integrated into a Situation-Task-Action-Consequence (STAC) classification model. This hybrid system, combining RoBERTa embeddings with the Expert Index, achieves superior precision in causal link identification compared to pure LLM-based approaches. Finally, a structured five-iteration prompting process refines and constructs connected causal graphs. Experiments on 100 narrative chapters and short stories demonstrate that our approach consistently outperforms GPT-4o and Claude 3.5 in causal graph quality, while maintaining readability. The open-source tool provides an interpretable, efficient solution for capturing nuanced causal chains in narratives.