Tootfinder

Tight Bounds for Answering Adaptively Chosen Concentrated Queries
Emma Rapoport, Edith Cohen, Uri Stemmer
https://arxiv.org/abs/2507.13700 https://

Tight Bounds for Answering Adaptively Chosen Concentrated Queries
Most work on adaptive data analysis assumes that samples in the dataset are independent. When correlations are allowed, even the non-adaptive setting can become intractable, unless some structural constraints are imposed. To address this, Bassily and Freund [2016] introduced the elegant framework of concentrated queries, which requires the analyst to restrict itself to queries that are concentrated around their expected value. While this assumption makes the problem trivial in the non-adaptive …

An Empirical Study on How Video-LLMs Answer Video Questions
Chenhui Gou, Ziyu Ma, Zicheng Duan, Haoyu He, Feng Chen, Akide Liu, Bohan Zhuang, Jianfei Cai, Hamid Rezatofighi
https://arxiv.org/abs/2508.15360

An Empirical Study on How Video-LLMs Answer Video Questions
Taking advantage of large-scale data and pretrained language models, Video Large Language Models (Video-LLMs) have shown strong capabilities in answering video questions. However, most existing efforts focus on improving performance, with limited attention to understanding their internal mechanisms. This paper aims to bridge this gap through a systematic empirical study. To interpret existing VideoLLMs, we adopt attention knockouts as our primary analytical tool and design three variants: Video…

AdaDocVQA: Adaptive Framework for Long Document Visual Question Answering in Low-Resource Settings
Haoxuan Li, Wei Song, Aofan Liu, Peiwu Qin
https://arxiv.org/abs/2508.13606 ht…

AdaDocVQA: Adaptive Framework for Long Document Visual Question Answering in Low-Resource Settings
Document Visual Question Answering (Document VQA) faces significant challenges when processing long documents in low-resource environments due to context limitations and insufficient training data. This paper presents AdaDocVQA, a unified adaptive framework addressing these challenges through three core innovations: a hybrid text retrieval architecture for effective document segmentation, an intelligent data augmentation pipeline that automatically generates high-quality reasoning question-answ…

APFEx: Adaptive Pareto Front Explorer for Intersectional Fairness
Priyobrata Mondal, Faizanuddin Ansari, Swagatam Das
https://arxiv.org/abs/2509.13908 https://

APFEx: Adaptive Pareto Front Explorer for Intersectional Fairness
Ensuring fairness in machine learning models is critical, especially when biases compound across intersecting protected attributes like race, gender, and age. While existing methods address fairness for single attributes, they fail to capture the nuanced, multiplicative biases faced by intersectional subgroups. We introduce Adaptive Pareto Front Explorer (APFEx), the first framework to explicitly model intersectional fairness as a joint optimization problem over the Cartesian product of sensiti…

AQUA-LLM: Evaluating Accuracy, Quantization, and Adversarial Robustness Trade-offs in LLMs for Cybersecurity Question Answering
Onat Gungor, Roshan Sood, Harold Wang, Tajana Rosing
https://arxiv.org/abs/2509.13514

AQUA-LLM: Evaluating Accuracy, Quantization, and Adversarial Robustness Trade-offs in LLMs for Cybersecurity Question Answering
Large Language Models (LLMs) have recently demonstrated strong potential for cybersecurity question answering (QA), supporting decision-making in real-time threat detection and response workflows. However, their substantial computational demands pose significant challenges for deployment on resource-constrained edge devices. Quantization, a widely adopted model compression technique, can alleviate these constraints. Nevertheless, quantization may degrade model accuracy and increase susceptibili…

Datarus-R1: An Adaptive Multi-Step Reasoning LLM for Automated Data Analysis
Ayoub Ben Chaliah, Hela Dellagi
https://arxiv.org/abs/2508.13382 https://arxiv…

Datarus-R1: An Adaptive Multi-Step Reasoning LLM for Automated Data Analysis
We present Datarus-R1-14B, a 14 B-parameter open-weights language model fine-tuned from Qwen 2.5-14B-Instruct to act as a virtual data analyst and graduate-level problem solver. Datarus is trained not on isolated question-answer pairs but on full analytical trajectories including reasoning steps, code execution, error traces, self-corrections, and final conclusions, all captured in a ReAct-style notebook format spanning finance, medicine, numerical analysis, and other quantitative domains. Our …

Breaking Reward Collapse: Adaptive Reinforcement for Open-ended Medical Reasoning with Enhanced Semantic Discrimination
Yizhou Liu, Jingwei Wei, Zizhi Chen, Minghao Han, Xukun Zhang, Keliang Liu, Lihua Zhang
https://arxiv.org/abs/2508.12957

Breaking Reward Collapse: Adaptive Reinforcement for Open-ended Medical Reasoning with Enhanced Semantic Discrimination
Reinforcement learning (RL) with rule-based rewards has demonstrated strong potential in enhancing the reasoning and generalization capabilities of vision-language models (VLMs) and large language models (LLMs), while reducing computational overhead. However, its application in medical imaging remains underexplored. Existing reinforcement fine-tuning (RFT) approaches in this domain primarily target closed-ended visual question answering (VQA), limiting their applicability to real-world clinical…

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…

PakBBQ: A Culturally Adapted Bias Benchmark for QA
Abdullah Hashmat, Muhammad Arham Mirza, Agha Ali Raza
https://arxiv.org/abs/2508.10186 https://arxiv.org…

PakBBQ: A Culturally Adapted Bias Benchmark for QA
With the widespread adoption of Large Language Models (LLMs) across various applications, it is empirical to ensure their fairness across all user communities. However, most LLMs are trained and evaluated on Western centric data, with little attention paid to low-resource languages and regional contexts. To address this gap, we introduce PakBBQ, a culturally and regionally adapted extension of the original Bias Benchmark for Question Answering (BBQ) dataset. PakBBQ comprises over 214 templates,…

An Agentic Toolkit for Adaptive Information Extraction from Regulatory Documents
Gaye Colakoglu, G\"urkan Solmaz, Jonathan F\"urst
https://arxiv.org/abs/2509.11773 htt…

An Agentic Toolkit for Adaptive Information Extraction from Regulatory Documents
Declaration of Performance (DoP) documents, mandated by EU regulation, certify the performance of construction products. While some of their content is standardized, DoPs vary widely in layout, language, schema, and format, posing challenges for automated key-value pair extraction (KVP) and question answering (QA). Existing static or LLM-only IE pipelines often hallucinate and fail to adapt to this structural diversity. Our domain-specific, stateful agentic system addresses these challenges thr…