Tootfinder

Confidence Estimation for Text-to-SQL in Large Language Models
Sepideh Entezari Maleki, Mohammadreza Pourreza, Davood Rafiei
https://arxiv.org/abs/2508.14056 https://

Confidence Estimation for Text-to-SQL in Large Language Models
Confidence estimation for text-to-SQL aims to assess the reliability of model-generated SQL queries without having access to gold answers. We study this problem in the context of large language models (LLMs), where access to model weights and gradients is often constrained. We explore both black-box and white-box confidence estimation strategies, evaluating their effectiveness on cross-domain text-to-SQL benchmarks. Our evaluation highlights the superior performance of consistency-based methods…

#ad new is good. Try the NEW! Sweet Chili Sauced and Tossed Chicken Strip Basket flavor! Available for a Limited Time at participating U.S. locations. Download the DQ app and get FREE delivery with a purchase of $25 or more in the DQ app. Terms apply. #happytastesgood @Dairy Queen

#Wordle 1,584 5/6*
⬜⬜⬜⬜🟨 <1% of 213,807 (150)
🟨🟨🟨⬜⬜ 0 of 29 (3)
⬜🟨🟨🟨⬜ 0 of 0 (1)
⬜🟩🟨🟩🟩 0 of 0 (1)
🟩🟩🟩🟩🟩
WordleBot
Skill 63/99
Luck 59/99
Killer wordle for me today. 1st user error on guess 3, then I could not think of ANY word for guess 4, was trying things at random, and it took what I would have thought was a proper name, and that got me the answer in guess 5!
Looked up guess 4 found other meanings, still not a wordle word.

2/2 Reflection on #citizenship:
I do not treat the concept of “#democracy" lightly. I was born into the aftermath of centuries of totalitarian oppression that ended suddenly, leaving the nascent Ukrainian state of the late 90s and early 2000s floundering in the turbulent whirlpool of hopes and fears felt by millions of people who were finally allowed to ponder: how to build a free democratic state in the place of Soviet and imperial ruins?
I was taught the words "democracy", "citizen", "freedom", "voting", “liberty" (and more) by people who, less than two decades prior, weren't allowed to leave the borders of their country. I was told about self-determination by people whose political choices were ridiculed, punished, and eviscerated form most of their lives. The duty of governing ourselves felt to us ephemeral - a nice fantasy, akin to a fairytale or a utopia from fictional works.
And then I saw those same people fight with their bodies and souls once the previously unfathomable democracy was threatened. Protests in 2004, then again in 2014, then the unthinkable war against foreign invasion in 2022. Democracy no longer felt abstract or silly. It became as tangible as saying "I love you".
I write of Ukraine as I reflect on becoming a citizen of another country because the history and values of my adopted United States feel as real as the skin on my legs, the significance of its legacy lays as heavy as the weight of my waist-long hair, and the desire to uphold the freedoms of its Constitution burns my throat as harshly as dehydration after a long day in the sun.
People have asked me why I even want to join this country, when the present moment is shrouded in impenetrable darkness. And I answer: because I've felt the warmth of a newly lit fire of freedom breaking through shadows that for centuries looked like solid walls. I have seen kindness, and solidarity heal the fear and hate of oppression. I've seen liberty emerge from nothing but the human soul.
I am not a religious person, but I have faith. Faith in the ideals at the foundation of the American project. Faint but powerful recognition that "we the people" now includes me.
I love #America. And I hope to keep loving my home for the rest of my life.

FRIT: Using Causal Importance to Improve Chain-of-Thought Faithfulness
Anand Swaroop, Akshat Nallani, Saksham Uboweja, Adiliia Uzdenova, Michael Nguyen, Kevin Zhu, Sunishchal Dev, Ashwinee Panda, Vasu Sharma, Maheep Chaudhary
https://arxiv.org/abs/2509.13334

FRIT: Using Causal Importance to Improve Chain-of-Thought Faithfulness
Chain-of-thought (CoT) reasoning has emerged as a powerful tool for improving large language model performance on complex tasks, but recent work shows that reasoning steps often fail to causally influence the final answer, creating brittle and untrustworthy outputs. Prior approaches focus primarily on measuring faithfulness, while methods for systematically improving it remain limited. We introduce Faithful Reasoning via Intervention Training (FRIT), a scalable alignment method that trains mode…

Cin\'{e}aste: A Fine-grained Contextual Movie Question Answering Benchmark
Nisarg A. Shah, Amir Ziai, Chaitanya Ekanadham, Vishal M. Patel
https://arxiv.org/abs/2509.14227 h…

Cinéaste: A Fine-grained Contextual Movie Question Answering Benchmark
While recent advancements in vision-language models have improved video understanding, diagnosing their capacity for deep, narrative comprehension remains a challenge. Existing benchmarks often test short-clip recognition or use template-based questions, leaving a critical gap in evaluating fine-grained reasoning over long-form narrative content. To address these gaps, we introduce $\mathsf{Cin\acute{e}aste}$, a comprehensive benchmark for long-form movie understanding. Our dataset comprises 3,…

Quelle surprise: seriöse Webseiten blocken den Zugang für KI-Trainingszugriff eher als Seiten, deren Zweck der Desinformation dient.
https://arxiv.org/abs/2510.10315

Omni-CLST: Error-aware Curriculum Learning with guided Selective chain-of-Thought for audio questuin answering
Jinghua Zhao, Hang Su, Lichun Fan, Zhenbo Luo, Jian Luan, Hui Wang, Haoqin Sun, Yong Qin
https://arxiv.org/abs/2509.12275

Omni-CLST: Error-aware Curriculum Learning with guided Selective chain-of-Thought for audio questuin answering
We propose Omni-CLST, an error-aware Curriculum Learning framework with guided Selective Chain-of-Thought for audio question answering. The framework efficiently leverages existing high-quality dataset through two key strategies: an error-aware curriculum that organizes samples by difficulty, and a guided thought dropout mechanism that focuses reasoning on challenging cases. Integrated with GRPO training, these strategies enable the model to learn more effectively from informative samples. Expe…

Slim-SC: Thought Pruning for Efficient Scaling with Self-Consistency
Colin Hong, Xu Guo, Anand Chaanan Singh, Esha Choukse, Dmitrii Ustiugov
https://arxiv.org/abs/2509.13990 htt…

Slim-SC: Thought Pruning for Efficient Scaling with Self-Consistency
Recently, Test-Time Scaling (TTS) has gained increasing attention for improving LLM reasoning performance at test time without retraining the model. A notable TTS technique is Self-Consistency (SC), which generates multiple reasoning chains in parallel and selects the final answer via majority voting. While effective, the order-of-magnitude computational overhead limits its broad deployment. Prior attempts to accelerate SC mainly rely on model-based confidence scores or heuristics with limited …

UnifiedVisual: A Framework for Constructing Unified Vision-Language Datasets
Pengyu Wang, Shaojun Zhou, Chenkun Tan, Xinghao Wang, Wei Huang, Zhen Ye, Zhaowei Li, Botian Jiang, Dong Zhang, Xipeng Qiu
https://arxiv.org/abs/2509.14738

UnifiedVisual: A Framework for Constructing Unified Vision-Language Datasets
Unified vision large language models (VLLMs) have recently achieved impressive advancements in both multimodal understanding and generation, powering applications such as visual question answering and text-guided image synthesis. However, progress in unified VLLMs remains constrained by the lack of datasets that fully exploit the synergistic potential between these two core abilities. Existing datasets typically address understanding and generation in isolation, thereby limiting the performance…