Tootfinder

MAPS: Masked Attribution-based Probing of Strategies- A computational framework to align human and model explanations
Sabine Muzellec, Yousif Kashef Alghetaa, Simon Kornblith, Kohitij Kar
https://arxiv.org/abs/2510.12141

MAPS: Masked Attribution-based Probing of Strategies- A computational framework to align human and model explanations
Human core object recognition depends on the selective use of visual information, but the strategies guiding these choices are difficult to measure directly. We present MAPS (Masked Attribution-based Probing of Strategies), a behaviorally validated computational tool that tests whether explanations derived from artificial neural networks (ANNs) can also explain human vision. MAPS converts attribution maps into explanation-masked images (EMIs) and compares image-by-image human accuracies on thes…

Information-Preserving Reformulation of Reasoning Traces for Antidistillation
Jiayu Ding, Lei Cui, Li Dong, Nanning Zheng, Furu Wei
https://arxiv.org/abs/2510.11545 https://

Information-Preserving Reformulation of Reasoning Traces for Antidistillation
Recent advances in Large Language Models (LLMs) show that extending the length of reasoning chains significantly improves performance on complex tasks. While revealing these reasoning traces helps users better follow, verify, and learn from the model's problem-solving process, it also makes them highly vulnerable to unauthorized distillation. To mitigate this risk, proprietary model providers often adopt aggressive protection strategies, such as replacing detailed reasoning with brief summaries…

Strategy Logic, Imperfect Information, and Hyperproperties
Raven Beutner, Bernd Finkbeiner
https://arxiv.org/abs/2510.03952 https://arxiv.org/pdf/2510.0395…

Strategy Logic, Imperfect Information, and Hyperproperties
Strategy logic (SL) is a powerful temporal logic that enables first-class reasoning over strategic behavior in multi-agent systems (MAS). In many MASs, the agents (and their strategies) cannot observe the global state of the system, leading to many extensions of SL centered around imperfect information, such as strategy logic with imperfect information (SL$_\mathit{ii}$). Along orthogonal lines, researchers have studied the combination of strategic behavior and hyperproperties. Hyperproperties …

User Prompting Strategies and ChatGPT Contextual Adaptation Shape Conversational Information-Seeking Experiences
Haoning Xue, Yoo Jung Oh, Xinyi Zhou, Xinyu Zhang, Berit Oxley
https://arxiv.org/abs/2509.25513

User Prompting Strategies and ChatGPT Contextual Adaptation Shape Conversational Information-Seeking Experiences
Conversational AI, such as ChatGPT, is increasingly used for information seeking. However, little is known about how ordinary users actually prompt and how ChatGPT adapts its responses in real-world conversational information seeking (CIS). In this study, a nationally representative sample of 937 U.S. adults engaged in multi-turn CIS with ChatGPT on both controversial and non-controversial topics across science, health, and policy contexts. We analyzed both user prompting strategies and the com…

Modelling and evaluating travel information during disruptions: An illustrative example from Swedish railways
Abderrahman Ait-Ali, Anders Peterson
https://arxiv.org/abs/2510.08254

Modelling and evaluating travel information during disruptions: An illustrative example from Swedish railways
Accurate and timely travel information is an asset for enhancing passenger travel experience during normal traffic, and for mitigating the discomforts during disruptions. With longer and more frequent disruptions as well as increasing ridership, traffic delays can incur substantial costs for passengers and other transport stakeholders, e.g., operators and infrastructure managers. Such costs can, however, be reduced thanks to effective travel information strategies during traffic disruptions. In…

Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric Retrieval
Yingyi Zhang, Pengyue Jia, Derong Xu, Yi Wen, Xianneng Li, Yichao Wang, Wenlin Zhang, Xiaopeng Li, Weinan Gan, Huifeng Guo, Yong Liu, Xiangyu Zhao
https://arxiv.org/abs/2510.08935

Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric Retrieval
Retrieval-Augmented Generation (RAG) critically depends on effective query expansion to retrieve relevant information. However, existing expansion methods adopt uniform strategies that overlook user-specific semantics, ignoring individual expression styles, preferences, and historical context. In practice, identical queries in text can express vastly different intentions across users. This representational rigidity limits the ability of current RAG systems to generalize effectively in personali…

Network Topology and Information Efficiency of Multi-Agent Systems: Study based on MARL
Xinren Zhang, Sixi Cheng, Zixin Zhong, Jiadong Yu
https://arxiv.org/abs/2510.07888 https:…

Network Topology and Information Efficiency of Multi-Agent Systems: Study based on MARL
Multi-agent systems (MAS) solve complex problems through coordinated autonomous entities with individual decision-making capabilities. While Multi-Agent Reinforcement Learning (MARL) enables these agents to learn intelligent strategies, it faces challenges of non-stationarity and partial observability. Communications among agents offer a solution, but questions remain about its optimal structure and evaluation. This paper explores two underexamined aspects: communication topology and informatio…

Complementarity Reveals Entanglement Sharing in Sequential Quantum Measurements
Zinuo Cai, Changliang Ren
https://arxiv.org/abs/2510.02710 https://arxiv.or…

Complementarity Reveals Entanglement Sharing in Sequential Quantum Measurements
We investigate entanglement sharing in a two-qubit sequential measurement scenario using three complementary classical correlation metrics: mutual information (I), sum of conditional probabilities (S), and the Pearson correlation coefficient (C). By investigating both weak measurement and probabilistic projective measurement (PPM) strategies in unilateral and bilateral scenarios, the phenomenon of entanglement sharing is conclusively certified when multiple pairs of classical correlation metric…

Constraint Satisfaction Approaches to Wordle: Novel Heuristics and Cross-Lexicon Validation
Jahidul Arafat, Fariha Tasmin, Sanjaya Poudel, Kamrujjaman, Eftakhar Ahmed Arnob, Ahsan Habib Tareq
https://arxiv.org/abs/2510.02855

Constraint Satisfaction Approaches to Wordle: Novel Heuristics and Cross-Lexicon Validation
Wordle presents an algorithmically rich testbed for constraint satisfaction problem (CSP) solving. While existing solvers rely on information-theoretic entropy maximization or frequency-based heuristics without formal constraint treatment, we present the first comprehensive CSP formulation of Wordle with novel constraint-aware solving strategies. We introduce CSP-Aware Entropy, computing information gain after constraint propagation rather than on raw candidate sets, and a Probabilistic CSP fra…

Collaborative Edge Inference via Semantic Grouping under Wireless Channel Constraints
Mateus P. Mota, Mattia Merluzzi, Emilio Calvanese Strinati
https://arxiv.org/abs/2510.02222

Collaborative Edge Inference via Semantic Grouping under Wireless Channel Constraints
In this paper, we study the framework of collaborative inference, or edge ensembles. This framework enables multiple edge devices to improve classification accuracy by exchanging intermediate features rather than raw observations. However, efficient communication strategies are essential to balance accuracy and bandwidth limitations. Building upon a key-query mechanism for selective information exchange, this work extends collaborative inference by studying the impact of channel noise in featur…

Wearable and Ultra-Low-Power Fusion of EMG and A-Mode US for Hand-Wrist Kinematic Tracking
Giusy Spacone, Sebastian Frey, Mattia Orlandi, Pierangelo Maria Rapa, Victor Kartsch, Simone Benatti, Luca Benini, Andrea Cossettini
https://arxiv.org/abs/2510.02000

Wearable and Ultra-Low-Power Fusion of EMG and A-Mode US for Hand-Wrist Kinematic Tracking
Hand gesture recognition based on biosignals has shown strong potential for developing intuitive human-machine interaction strategies that closely mimic natural human behavior. In particular, sensor fusion approaches have gained attention for combining complementary information and overcoming the limitations of individual sensing modalities, thereby enabling more robust and reliable systems. Among them, the fusion of surface electromyography (EMG) and A-mode ultrasound (US) is very promising. H…

TRUE: A Reproducible Framework for LLM-Driven Relevance Judgment in Information Retrieval
Mouly Dewan, Jiqun Liu, Chirag Shah
https://arxiv.org/abs/2509.25602 https://

TRUE: A Reproducible Framework for LLM-Driven Relevance Judgment in Information Retrieval
LLM-based relevance judgment generation has become a crucial approach in advancing evaluation methodologies in Information Retrieval (IR). It has progressed significantly, often showing high correlation with human judgments as reflected in LLMJudge leaderboards \cite{rahmani2025judging}. However, existing methods for relevance judgments, rely heavily on sensitive prompting strategies, lacking standardized workflows for generating reliable labels. To fill this gap, we reintroduce our method, \te…

Towards Human-Centered RegTech: Unpacking Professionals' Strategies and Needs for Using LLMs Safely
Siying Hu, Yaxing Yao, Zhicong Lu
https://arxiv.org/abs/2510.01638 https:…

Towards Human-Centered RegTech: Unpacking Professionals' Strategies and Needs for Using LLMs Safely
Large Language Models are profoundly changing work patterns in high-risk professional domains, yet their application also introduces severe and underexplored compliance risks. To investigate this issue, we conducted semi-structured interviews with 24 highly-skilled knowledge workers from industries such as law, healthcare, and finance. The study found that these experts are commonly concerned about sensitive information leakage, intellectual property infringement, and uncertainty regarding the …

Bandits roaming Hilbert space
Josep Lumbreras
https://arxiv.org/abs/2509.24569 https://arxiv.org/pdf/2509.24569

Bandits roaming Hilbert space
This thesis studies the exploration and exploitation trade-off in online learning of properties of quantum states using multi-armed bandits. Given streaming access to an unknown quantum state, in each round we select an observable from a set of actions to maximize its expectation value. Using past information, we refine actions to minimize regret; the cumulative gap between current reward and the maximum possible. We derive information-theoretic lower bounds and optimal strategies with matching…

"Shall We Dig Deeper?": Designing and Evaluating Strategies for LLM Agents to Advance Knowledge Co-Construction in Asynchronous Online Discussions
Yuanhao Zhang, Wenbo Li, Xiaoyu Wang, Kangyu Yuan, Shuai Ma, Xiaojuan Ma
https://arxiv.org/abs/2509.23327

"Shall We Dig Deeper?": Designing and Evaluating Strategies for LLM Agents to Advance Knowledge Co-Construction in Asynchronous Online Discussions
Asynchronous online discussions enable diverse participants to co-construct knowledge beyond individual contributions. This process ideally evolves through sequential phases, from superficial information exchange to deeper synthesis. However, many discussions stagnate in the early stages. Existing AI interventions typically target isolated phases, lacking mechanisms to progressively advance knowledge co-construction, and the impacts of different intervention styles in this context remain unclea…

Efficient and Versatile Model for Multilingual Information Retrieval of Islamic Text: Development and Deployment in Real-World Scenarios
Vera Pavlova, Mohammed Makhlouf
https://arxiv.org/abs/2509.15380

Efficient and Versatile Model for Multilingual Information Retrieval of Islamic Text: Development and Deployment in Real-World Scenarios
Despite recent advancements in Multilingual Information Retrieval (MLIR), a significant gap remains between research and practical deployment. Many studies assess MLIR performance in isolated settings, limiting their applicability to real-world scenarios. In this work, we leverage the unique characteristics of the Quranic multilingual corpus to examine the optimal strategies to develop an ad-hoc IR system for the Islamic domain that is designed to satisfy users' information needs in multiple la…

Inverse-Designed Photonic Crystal Cavities with Controllable Far-Field Numerical Aperture
Neelesh Kumar Vij, Purbita Purkayastha, Jasvith Raj Basani, Edo Waks
https://arxiv.org/abs/2509.16827

Inverse-Designed Photonic Crystal Cavities with Controllable Far-Field Numerical Aperture
Photonic crystal cavities confine light to subwavelength volumes, enabling strong light-matter interactions for applications in low-power photonics, opto-electronics, nonlinear optics, and quantum information. These applications demand cavities that combine high quality factors, low mode volumes, and high coupling efficiencies. However, optimizing across these metrics requires exploring a large design space, motivating the use of inverse design strategies. Previous inverse design efforts target…

UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression
Chenlong Deng, Zhisong Zhang, Kelong Mao, Shuaiyi Li, Tianqing Fang, Hongming Zhang, Haitao Mi, Dong Yu, Zhicheng Dou
https://arxiv.org/abs/2509.15763

UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression
Large language models are increasingly capable of handling long-context inputs, but the memory overhead of key-value (KV) cache remains a major bottleneck for general-purpose deployment. While various compression strategies have been explored, sequence-level compression, which drops the full KV caches for certain tokens, is particularly challenging as it can lead to the loss of important contextual information. To address this, we introduce UniGist, a sequence-level long-context compression fra…

How People Manage Knowledge in their "Second Brains"- A Case Study with Industry Researchers Using Obsidian
Juliana Jansen Ferreira, Vin\'icius Segura, Joana Gabriela Souza, Joao Henrique Gallas Brasil
https://arxiv.org/abs/2509.20187

How People Manage Knowledge in their "Second Brains"- A Case Study with Industry Researchers Using Obsidian
People face overwhelming information during work activities, necessitating effective organization and management strategies. Even in personal lives, individuals must keep, annotate, organize, and retrieve knowledge from daily routines. The collection of records for future reference is known as a personal knowledge base. Note-taking applications are valuable tools for building and maintaining these bases, often called a ''second brain''. This paper presents a case study on how people build and e…