Tootfinder

PersonaTeaming: Exploring How Introducing Personas Can Improve Automated AI Red-Teaming
Wesley Hanwen Deng, Sunnie S. Y. Kim, Akshita Jha, Ken Holstein, Motahhare Eslami, Lauren Wilcox, Leon A Gatys
https://arxiv.org/abs/2509.03728

PersonaTeaming: Exploring How Introducing Personas Can Improve Automated AI Red-Teaming
Recent developments in AI governance and safety research have called for red-teaming methods that can effectively surface potential risks posed by AI models. Many of these calls have emphasized how the identities and backgrounds of red-teamers can shape their red-teaming strategies, and thus the kinds of risks they are likely to uncover. While automated red-teaming approaches promise to complement human red-teaming by enabling larger-scale exploration of model behavior, current approaches do no…

heute & morgen nehme ich an der VDB- und @CrossAsia-Online-Fortbildung für Fachreferent:innen und Bibliothekar:innen der Asienwissenschaften 2025: https://blog.crossasia.org/vdb-online-fortbildung-2025/. 🎧
ich kann die fächer, die wir aus dem themenspektrum in münster h…

Towards a Unified View of Large Language Model Post-Training
Xingtai Lv, Yuxin Zuo, Youbang Sun, Hongyi Liu, Yuntian Wei, Zhekai Chen, Lixuan He, Xuekai Zhu, Kaiyan Zhang, Bingning Wang, Ning Ding, Bowen Zhou
https://arxiv.org/abs/2509.04419

Towards a Unified View of Large Language Model Post-Training
Two major sources of training data exist for post-training modern language models: online (model-generated rollouts) data, and offline (human or other-model demonstrations) data. These two types of data are typically used by approaches like Reinforcement Learning (RL) and Supervised Fine-Tuning (SFT), respectively. In this paper, we show that these approaches are not in contradiction, but are instances of a single optimization process. We derive a Unified Policy Gradient Estimator, and present …

Format Inertia: A Failure Mechanism of LLMs in Medical Pre-Consultation
Seungseop Lim, Gibaeg Kim, Wooseok Han, Jean Seo, Hyunkyung Lee, Jaehyo Yoo, Eunho Yang
https://arxiv.org/abs/2510.01688

Format Inertia: A Failure Mechanism of LLMs in Medical Pre-Consultation
Recent advances in Large Language Models (LLMs) have brought significant improvements to various service domains, including chatbots and medical pre-consultation applications. In the healthcare domain, the most common approach for adapting LLMs to multi-turn dialogue generation is Supervised Fine-Tuning (SFT). However, datasets for SFT in tasks like medical pre-consultation typically exhibit a skewed turn-count distribution. Training on such data induces a novel failure mechanism we term **Form…

AI-CNet3D: An Anatomically-Informed Cross-Attention Network with Multi-Task Consistency Fine-tuning for 3D Glaucoma Classification
Roshan Kenia, Anfei Li, Rishabh Srivastava, Kaveri A. Thakoor
https://arxiv.org/abs/2510.00882

AI-CNet3D: An Anatomically-Informed Cross-Attention Network with Multi-Task Consistency Fine-tuning for 3D Glaucoma Classification
Glaucoma is a progressive eye disease that leads to optic nerve damage, causing irreversible vision loss if left untreated. Optical coherence tomography (OCT) has become a crucial tool for glaucoma diagnosis, offering high-resolution 3D scans of the retina and optic nerve. However, the conventional practice of condensing information from 3D OCT volumes into 2D reports often results in the loss of key structural details. To address this, we propose a novel hybrid deep learning model that integra…

The Very Faint X-ray Transient 4XMM J174610.7-290020 at the Galactic center
Giovanni Stel, Gabriele Ponti, Nathalie Degenaar, Lara Sidoli, Sandro Mereghetti, Kaya Mori, Tong Bao, Giulia Illiano, Samaresh Mondal, Mark Reynolds, Chichuan Jin, Tianying Lian, Shifra Mandel, Simone Scaringi, Shuo Zhang, Grace Sanger-Johnson, Rudy Wijnands, Jon M. Miller, Jamie Kennea, Zhenlin Zhu

The Very Faint X-ray Transient 4XMM J174610.7-290020 at the Galactic center
Very Faint X-ray Transients (VFXTs) are a class of X-ray binary systems that exhibit occasional outbursts with peak X-ray luminosities (L_X< 1e36 erg s^-1) much lower than typical X-ray transients. On 22nd February 2024, during its daily Galactic center monitoring, Swift-XRT detected a VFXT, 7 arcmin from Sgr A* dubbing it Swift J174610--290018. We aim to characterize the outburst that occurred in 2024, and a second, distinct outburst in 2025, to understand the nature and accretion flow propert…

How Well Do Vision--Language Models Understand Cities? A Comparative Study on Spatial Reasoning from Street-View Images
Juneyoung Ro, Namwoo Kim, Yoonjin Yoon
https://arxiv.org/abs/2508.21565

How Well Do Vision--Language Models Understand Cities? A Comparative Study on Spatial Reasoning from Street-View Images
Effectively understanding urban scenes requires fine-grained spatial reasoning about objects, layouts, and depth cues. However, how well current vision-language models (VLMs), pretrained on general scenes, transfer these abilities to urban domain remains underexplored. To address this gap, we conduct a comparative study of three off-the-shelf VLMs-BLIP-2, InstructBLIP, and LLaVA-1.5-evaluating both zero-shot performance and the effects of fine-tuning with a synthetic VQA dataset specific to urb…

Adaptive Planning for Multi-Attribute Controllable Summarization with Monte Carlo Tree Search
Sangwon Ryu, Heejin Do, Yunsu Kim, Gary Geunbae Lee, Jungseul Ok
https://arxiv.org/abs/2509.26435

Adaptive Planning for Multi-Attribute Controllable Summarization with Monte Carlo Tree Search
Controllable summarization moves beyond generic outputs toward human-aligned summaries guided by specified attributes. In practice, the interdependence among attributes makes it challenging for language models to satisfy correlated constraints consistently. Moreover, previous approaches often require per-attribute fine-tuning, limiting flexibility across diverse summary attributes. In this paper, we propose adaptive planning for multi-attribute controllable summarization (PACO), a training-free…

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[3/5]:
- Medical Red Teaming Protocol of Language Models: On the Importance of User Perspectives in Health...
Jean-Philippe Corbeil, Minseon Kim, Alessandro Sordoni, Francois Beaulieu, Paul Vozila

ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuning
Yiming Du, Yifan Xiang, Bin Liang, Dahua Lin, Kam-Fai Wong, Fei Tan
https://arxiv.org/abs/2508.19996

ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuning
Fine-tuning multi-turn dialogue systems requires high-quality supervision but often suffers from degraded performance when exposed to low-quality data. Supervision errors in early turns can propagate across subsequent turns, undermining coherence and response quality. Existing methods typically address data quality via static prefiltering, which decouples quality control from training and fails to mitigate turn-level error propagation. In this context, we propose ReSURE (Regularizing Supervisio…