Tootfinder

A Computational Approach to Analyzing Language Change and Variation in the Constructed Language Toki Pona
Daniel Huang, Hyoun-A Joo
https://arxiv.org/abs/2508.10246 https://

A Computational Approach to Analyzing Language Change and Variation in the Constructed Language Toki Pona
This study explores language change and variation in Toki Pona, a constructed language with approximately 120 core words. Taking a computational and corpus-based approach, the study examines features including fluid word classes and transitivity in order to examine (1) changes in preferences of content words for different syntactic positions over time and (2) variation in usage across different corpora. The results suggest that sociolinguistic factors influence Toki Pona in the same way as natu…

Adapting and Evaluating Multimodal Large Language Models for Adolescent Idiopathic Scoliosis Self-Management: A Divide and Conquer Framework
Zhaolong Wu, Pu Luo, Jason Pui Yin Cheung, Teng Zhang
https://arxiv.org/abs/2509.11645

Adapting and Evaluating Multimodal Large Language Models for Adolescent Idiopathic Scoliosis Self-Management: A Divide and Conquer Framework
This study presents the first comprehensive evaluation of Multimodal Large Language Models (MLLMs) for Adolescent Idiopathic Scoliosis (AIS) self-management. We constructed a database of approximately 3,000 anteroposterior X-rays with diagnostic texts and evaluated five MLLMs through a `Divide and Conquer' framework consisting of a visual question-answering task, a domain knowledge assessment task, and a patient education counseling assessment task. Our investigation revealed limitations of MLL…

DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Search
Kartik Narayan, Yang Xu, Tian Cao, Kavya Nerella, Vishal M. Patel, Navid Shiee, Peter Grasch, Chao Jia, Yinfei Yang, Zhe Gan
https://arxiv.org/abs/2510.12801

DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Search
Multimodal Large Language Models (MLLMs) in real-world applications require access to external knowledge sources and must remain responsive to the dynamic and ever-changing real-world information in order to address information-seeking and knowledge-intensive user queries. Existing approaches, such as retrieval augmented generation (RAG) methods, search agents, and search equipped MLLMs, often suffer from rigid pipelines, excessive search calls, and poorly constructed search queries, which resu…

Securing Agentic AI: Threat Modeling and Risk Analysis for Network Monitoring Agentic AI System
Pallavi Zambare, Venkata Nikhil Thanikella, Ying Liu
https://arxiv.org/abs/2508.10043

Securing Agentic AI: Threat Modeling and Risk Analysis for Network Monitoring Agentic AI System
When combining Large Language Models (LLMs) with autonomous agents, used in network monitoring and decision-making systems, this will create serious security issues. In this research, the MAESTRO framework consisting of the seven layers threat modeling architecture in the system was used to expose, evaluate, and eliminate vulnerabilities of agentic AI. The prototype agent system was constructed and implemented, using Python, LangChain, and telemetry in WebSockets, and deployed with inference, m…

SocioBench: Modeling Human Behavior in Sociological Surveys with Large Language Models
Jia Wang, Ziyu Zhao, Tingjuntao Ni, Zhongyu Wei
https://arxiv.org/abs/2510.11131 https://

SocioBench: Modeling Human Behavior in Sociological Surveys with Large Language Models
Large language models (LLMs) show strong potential for simulating human social behaviors and interactions, yet lack large-scale, systematically constructed benchmarks for evaluating their alignment with real-world social attitudes. To bridge this gap, we introduce SocioBench-a comprehensive benchmark derived from the annually collected, standardized survey data of the International Social Survey Programme (ISSP). The benchmark aggregates over 480,000 real respondent records from more than 30 co…

Artificial Authority: From Machine Minds to Political Alignments. An Experimental Analysis of Democratic and Autocratic Biases in Large-Language Models
Szymon {\L}ukasik, Natalia O\.zegalska-{\L}ukasik
https://arxiv.org/abs/2509.25286

Artificial Authority: From Machine Minds to Political Alignments. An Experimental Analysis of Democratic and Autocratic Biases in Large-Language Models
Political beliefs vary significantly across different countries, reflecting distinct historical, cultural, and institutional contexts. These ideologies, ranging from liberal democracies to rigid autocracies, influence human societies, as well as the digital systems that are constructed within those societies. The advent of generative artificial intelligence, particularly Large Language Models (LLMs), introduces new agents in the political space-agents trained on massive corpora that replicate a…

i think "terrorism" is a case where it's best to meet the culture where it's at. language isn't prescribed by the dictionary. while the people shouldn't just let decades of government propaganda dictate the meaning of a word, its literally constructed with "terror" in the name from the get go, and that alone means there's triple the pressure there yall will never have the numbers and influence to beat. its okay if they think the terrorism accusation is…

MapAgent: Trajectory-Constructed Memory-Augmented Planning for Mobile Task Automation
Yi Kong, Dianxi Shi, Guoli Yang, Zhang ke-di, Chenlin Huang, Xiaopeng Li, Songchang Jin
https://arxiv.org/abs/2507.21953

MapAgent: Trajectory-Constructed Memory-Augmented Planning for Mobile Task Automation
The recent advancement of autonomous agents powered by Large Language Models (LLMs) has demonstrated significant potential for automating tasks on mobile devices through graphical user interfaces (GUIs). Despite initial progress, these agents still face challenges when handling complex real-world tasks. These challenges arise from a lack of knowledge about real-life mobile applications in LLM-based agents, which may lead to ineffective task planning and even cause hallucinations. To address the…

Prometheus: Unified Knowledge Graphs for Issue Resolution in Multilingual Codebases
Zimin Chen, Yue Pan, Siyu Lu, Jiayi Xu, Claire Le Goues, Martin Monperrus, He Ye
https://arxiv.org/abs/2507.19942

Prometheus: Unified Knowledge Graphs for Issue Resolution in Multilingual Codebases
Language model (LM) agents, such as SWE-agent and OpenHands, have made progress toward automated issue resolution. However, existing approaches are often limited to Python-only issues and rely on pre-constructed containers in SWE-bench with reproduced issues, restricting their applicability to real-world and work for multi-language repositories. We present Prometheus, designed to resolve real-world issues beyond benchmark settings. Prometheus is a multi-agent system that transforms an entire co…

CompLex: Music Theory Lexicon Constructed by Autonomous Agents for Automatic Music Generation
Zhejing Hu, Yan Liu, Gong Chen, Bruce X. B. Yu
https://arxiv.org/abs/2508.19603 htt…

CompLex: Music Theory Lexicon Constructed by Autonomous Agents for Automatic Music Generation
Generative artificial intelligence in music has made significant strides, yet it still falls short of the substantial achievements seen in natural language processing, primarily due to the limited availability of music data. Knowledge-informed approaches have been shown to enhance the performance of music generation models, even when only a few pieces of musical knowledge are integrated. This paper seeks to leverage comprehensive music theory in AI-driven music generation tasks, such as algorit…

Concept Unlearning in Large Language Models via Self-Constructed Knowledge Triplets
Tomoya Yamashita, Yuuki Yamanaka, Masanori Yamada, Takayuki Miura, Toshiki Shibahara, Tomoharu Iwata
https://arxiv.org/abs/2509.15621

Concept Unlearning in Large Language Models via Self-Constructed Knowledge Triplets
Machine Unlearning (MU) has recently attracted considerable attention as a solution to privacy and copyright issues in large language models (LLMs). Existing MU methods aim to remove specific target sentences from an LLM while minimizing damage to unrelated knowledge. However, these approaches require explicit target sentences and do not support removing broader concepts, such as persons or events. To address this limitation, we introduce Concept Unlearning (CU) as a new requirement for LLM unl…

MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks
Yadong Niu, Tianzi Wang, Heinrich Dinkel, Xingwei Sun, Jiahao Zhou, Gang Li, Jizhong Liu, Xunying Liu, Junbo Zhang, Jian Luan
https://arxiv.org/abs/2507.23511

MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks
While large audio-language models have advanced open-ended audio understanding, they still fall short of nuanced human-level comprehension. This gap persists largely because current benchmarks, limited by data annotations and evaluation metrics, fail to reliably distinguish between generic and highly detailed model outputs. To this end, this work introduces MECAT, a Multi-Expert Constructed Benchmark for Fine-Grained Audio Understanding Tasks. Generated via a pipeline that integrates analysis f…

LLM4MG: Adapting Large Language Model for Multipath Generation via Synesthesia of Machines
Ziwei Huang, Shiliang Lu, Lu Bai, Xuesong Cai, Xiang Cheng
https://arxiv.org/abs/2509.14711

LLM4MG: Adapting Large Language Model for Multipath Generation via Synesthesia of Machines
Based on Synesthesia of Machines (SoM), a large language model (LLM) is adapted for multipath generation (LLM4MG) for the first time. Considering a typical sixth-generation (6G) vehicle-to-infrastructure (V2I) scenario, a new multi-modal sensing-communication dataset is constructed, named SynthSoM-V2I, including channel multipath information, millimeter wave (mmWave) radar sensory data, RGB-D images, and light detection and ranging (LiDAR) point clouds. Based on the SynthSoM-V2I dataset, the pr…

Designing Shadow Tomography Protocols by Natural Language Processing
Yadong Wu, Pengfei Zhang, Ce Wang, Juan Yao, Yi-Zhuang You
https://arxiv.org/abs/2509.12782 https://

Designing Shadow Tomography Protocols by Natural Language Processing
Quantum circuits form a foundational framework in quantum science, enabling the description, analysis, and implementation of quantum computations. However, designing efficient circuits, typically constructed from single- and two-qubit gates, remains a major challenge for specific computational tasks. In this work, we introduce a novel artificial intelligence-driven protocol for quantum circuit design, benchmarked using shadow tomography for efficient quantum state readout. Inspired by technique…

Solution for Meta KDD Cup'25: A Comprehensive Three-Step Framework for Vision Question Answering
Zijian Zhang, Xiaocheng Zhang, Yang Zhou, Zhimin Lin, Peng Yan
https://arxiv.org/abs/2507.21520

Solution for Meta KDD Cup'25: A Comprehensive Three-Step Framework for Vision Question Answering
Vision Large Language Models (VLLMs) have improved multi-modal understanding and visual question answering (VQA), but still suffer from hallucinated answers. Multi-modal Retrieval-Augmented Generation (RAG) helps address these issues by incorporating external information, yet challenges remain in visual context comprehension, multi-source retrieval, and multi-turn interactions. To address these challenges, Meta constructed the CRAG-MM benchmark and launched the CRAG-MM Challenge at KDD Cup 2025…

Mamba Outpaces Reformer in Stock Prediction with Sentiments from Top Ten LLMs
Lokesh Antony Kadiyala, Amir Mirzaeinia
https://arxiv.org/abs/2510.01203 https://

Mamba Outpaces Reformer in Stock Prediction with Sentiments from Top Ten LLMs
The stock market is extremely difficult to predict in the short term due to high market volatility, changes caused by news, and the non-linear nature of the financial time series. This research proposes a novel framework for improving minute-level prediction accuracy using semantic sentiment scores from top ten different large language models (LLMs) combined with minute interval intraday stock price data. We systematically constructed a time-aligned dataset of AAPL news articles and 1-minute Ap…

Weighing Obese Timed Languages
Eugene Asarin, Aldric Degorre, Catalin Dima, Bernardo Jacobo Incl\'an
https://arxiv.org/abs/2508.18133 https://arxiv.org…

Weighing Obese Timed Languages
The bandwidth of a timed language characterizes the quantity of information per time unit (with a finite observation precision $\varepsilon$). Obese timed automata have an unbounded frequency of events and produce information at the maximal possible rate. In this article, we compute the bandwidth of any such automaton in the form $\approxα/\varepsilon$. Our approach reduces the problem to computing the best reward-to-time ratio in a weighted timed graph constructed from the given timed automat…

Subjective Behaviors and Preferences in LLM: Language of Browsing
Sai Sundaresan, Harshita Chopra, Atanu R. Sinha, Koustava Goswami, Nagasai Saketh Naidu, Raghav Karan, N Anushka
https://arxiv.org/abs/2508.15474

Subjective Behaviors and Preferences in LLM: Language of Browsing
A Large Language Model (LLM) offers versatility across domains and tasks, purportedly benefiting users with a wide variety of behaviors and preferences. We question this perception about an LLM when users have inherently subjective behaviors and preferences, as seen in their ubiquitous and idiosyncratic browsing of websites or apps. The sequential behavior logs of pages, thus generated, form something akin to each user's self-constructed "language", albeit without the structure and grammar imbu…

Fractal Illusions: An Experimental Study of Long-Range Sentence-Length Correlations in Randomly Generated Natural Language Texts
Ying Zeng, Junying Cui, Lejun Li
https://arxiv.org/abs/2508.19782

Fractal Illusions: An Experimental Study of Long-Range Sentence-Length Correlations in Randomly Generated Natural Language Texts
This study re-evaluates the assumption that long-range correlations in sentence length are a fundamental feature of natural language and a marker of literary style. While previous research has suggested that punctuation marks--particularly full stops--generate structural regularities in narrative texts, our experiments challenge this view. Using Chinese as the primary language, supplemented with English, we constructed randomized linguistic sequences through three distinct methods. Surprisingly…

From Ground Trust to Truth: Disparities in Offensive Language Judgments on Contemporary Korean Political Discourse
Seunguk Yu, Jungmin Yun, Jinhee Jang, Youngbin Kim
https://arxiv.org/abs/2509.14712

From Ground Trust to Truth: Disparities in Offensive Language Judgments on Contemporary Korean Political Discourse
Although offensive language continually evolves over time, even recent studies using LLMs have predominantly relied on outdated datasets and rarely evaluated the generalization ability on unseen texts. In this study, we constructed a large-scale dataset of contemporary political discourse and employed three refined judgments in the absence of ground truth. Each judgment reflects a representative offensive language detection method and is carefully designed for optimal conditions. We identified …

A Generative AI System for Biomedical Data Discovery with Grammar-Based Visualizations
Devin Lange, Shanghua Gao, Pengwei Sui, Austen Money, Priya Misner, Marinka Zitnik, Nils Gehlenborg
https://arxiv.org/abs/2509.16454

A Generative AI System for Biomedical Data Discovery with Grammar-Based Visualizations
We explore the potential for combining generative AI with grammar-based visualizations for biomedical data discovery. In our prototype, we use a multi-agent system to generate visualization specifications and apply filters. These visualizations are linked together, resulting in an interactive dashboard that is progressively constructed. Our system leverages the strengths of natural language while maintaining the utility of traditional user interfaces. Furthermore, we utilize generated interacti…

Measuring Bias or Measuring the Task: Understanding the Brittle Nature of LLM Gender Biases
Bufan Gao, Elisa Kreiss
https://arxiv.org/abs/2509.04373 https://

Measuring Bias or Measuring the Task: Understanding the Brittle Nature of LLM Gender Biases
As LLMs are increasingly applied in socially impactful settings, concerns about gender bias have prompted growing efforts both to measure and mitigate such bias. These efforts often rely on evaluation tasks that differ from natural language distributions, as they typically involve carefully constructed task prompts that overtly or covertly signal the presence of gender bias-related content. In this paper, we examine how signaling the evaluative purpose of a task impacts measured gender bias in …

TRACY: Benchmarking Execution Efficiency of LLM-Based Code Translation
Zhihao Gong, Zeyu Sun, Dong Huang, Qingyuan Liang, Jie M. Zhang, Dan Hao
https://arxiv.org/abs/2508.11468 …

TRACY: Benchmarking Execution Efficiency of LLM-Based Code Translation
Automatic code translation is a fundamental task in modern software development. While the advent of Large Language Models (LLMs) has significantly improved the correctness of code translation, the critical dimension of execution efficiency remains overlooked. To address this gap, we introduce TRACY, the first comprehensive benchmark designed to evaluate the execution efficiency of LLM-translated code. TRACY is constructed through an LLM-driven two-stage pipeline: an initial stage generates a s…

TianHui: A Domain-Specific Large Language Model for Diverse Traditional Chinese Medicine Scenarios
Ji Yin, Menglan He, Yujie Zhang, Linshuai Zhang, Tingting Ma, Ce Tian, Jie Wu, Lin Xu, Tao Jiang
https://arxiv.org/abs/2509.19834

TianHui: A Domain-Specific Large Language Model for Diverse Traditional Chinese Medicine Scenarios
Domain-specific LLMs in TCM face limitations in research settings due to constrained adaptability, insufficient evaluation datasets, and limited computational resources. This study presents TianHui, a specialized TCM LLM built through contextual data integration and domain knowledge fusion. We constructed a large-scale TCM corpus (0.97GB unsupervised data + 611,312 QA pairs) and employed a two-stage training strategy with QLoRA, DeepSpeed Stage 2, and Flash Attention 2. Evaluation on 12 benchma…

Discipline and Resistance: The Construction of a Digital Home for TikTok Refugees on Xiaohongshu
Xiaoyu Xiong, Yuting Peng, Summer Kwong, Anqi Huang
https://arxiv.org/abs/2507.14465

Discipline and Resistance: The Construction of a Digital Home for TikTok Refugees on Xiaohongshu
This study examines how TikTok refugees moved to Xiaohongshu after TikTok was about to be banned in the United States. It utilizes Foucault's idea of heterotopia to demonstrate how Xiaohongshu became a crisis space for cross-cultural discussions across the Great Firewall. Through Critical Discourse Analysis of 586 user comments, the study reveals how Chinese and international users collaboratively constructed and contested a new online order through language negotiation, identity positioning, a…

Humans learn to prefer trustworthy AI over human partners
Yaomin Jiang, Levin Brinkmann, Anne-Marie Nussberger, Ivan Soraperra, Jean-Fran\c{c}ois Bonnefon, Iyad Rahwan
https://arxiv.org/abs/2507.13524

Humans learn to prefer trustworthy AI over human partners
Partner selection is crucial for cooperation and hinges on communication. As artificial agents, especially those powered by large language models (LLMs), become more autonomous, intelligent, and persuasive, they compete with humans for partnerships. Yet little is known about how humans select between human and AI partners and adapt under AI-induced competition pressure. We constructed a communication-based partner selection game and examined the dynamics in hybrid mini-societies of humans and b…

Incorporating LLM Embeddings for Variation Across the Human Genome
Hongqian Niu, Jordan Bryan, Xihao Li, Didong Li
https://arxiv.org/abs/2509.20702 https://

Incorporating LLM Embeddings for Variation Across the Human Genome
Recent advances in large language model (LLM) embeddings have enabled powerful representations for biological data, but most applications to date focus only on gene-level information. We present one of the first systematic frameworks to generate variant-level embeddings across the entire human genome. Using curated annotations from FAVOR, ClinVar, and the GWAS Catalog, we constructed semantic text descriptions for 8.9 billion possible variants and generated embeddings at three scales: 1.5 milli…

ToxiFrench: Benchmarking and Enhancing Language Models via CoT Fine-Tuning for French Toxicity Detection
Axel Delaval, Shujian Yang, Haicheng Wang, Han Qiu, Jialiang Lu
https://arxiv.org/abs/2508.11281

ToxiFrench: Benchmarking and Enhancing Language Models via CoT Fine-Tuning for French Toxicity Detection
Detecting toxic content using language models is crucial yet challenging. While substantial progress has been made in English, toxicity detection in French remains underdeveloped, primarily due to the lack of culturally relevant, large-scale datasets. In this work, we introduce TOXIFRENCH, a new public benchmark of 53,622 French online comments, constructed via a semi-automated annotation pipeline that reduces manual labeling to only 10% through high-confidence LLM-based pre-annotation and huma…

Soft Injection of Task Embeddings Outperforms Prompt-Based In-Context Learning
Jungwon Park, Wonjong Rhee
https://arxiv.org/abs/2507.20906 https://arxiv.or…

Soft Injection of Task Embeddings Outperforms Prompt-Based In-Context Learning
In-Context Learning (ICL) enables Large Language Models (LLMs) to perform tasks by conditioning on input-output examples in the prompt, without requiring any update in model parameters. While widely adopted, it remains unclear whether prompting with multiple examples is the most effective and efficient way to convey task information. In this work, we propose Soft Injection of task embeddings. The task embeddings are constructed only once using few-shot ICL prompts and repeatedly used during inf…

Feedback Indicators: The Alignment between Llama and a Teacher in Language Learning
Sylvio R\"udian, Yassin Elsir, Marvin Kretschmer, Sabine Cayrou, Niels Pinkwart
https://arxiv.org/abs/2508.11364

Feedback Indicators: The Alignment between Llama and a Teacher in Language Learning
Automated feedback generation has the potential to enhance students' learning progress by providing timely and targeted feedback. Moreover, it can assist teachers in optimizing their time, allowing them to focus on more strategic and personalized aspects of teaching. To generate high-quality, information-rich formative feedback, it is essential first to extract relevant indicators, as these serve as the foundation upon which the feedback is constructed. Teachers often employ feedback criteria g…