Tootfinder

An Anthropologist LLM to Elicit Users' Moral Preferences through Role-Play
Gianluca De Ninno, Paola Inverardi, Francesca Belotti
https://arxiv.org/abs/2510.01189 https://

An Anthropologist LLM to Elicit Users' Moral Preferences through Role-Play
This study investigates a novel approach to eliciting users' moral decision-making by combining immersive roleplaying games with LLM analysis capabilities. Building on the distinction introduced by Floridi between hard ethics inspiring and shaping laws-and soft ethics-moral preferences guiding individual behavior within the free space of decisions compliant to laws-we focus on capturing the latter through contextrich, narrative-driven interactions. Grounded in anthropological methods, the role-…

The Alignment Waltz: Jointly Training Agents to Collaborate for Safety
Jingyu Zhang, Haozhu Wang, Eric Michael Smith, Sid Wang, Amr Sharaf, Mahesh Pasupuleti, Benjamin Van Durme, Daniel Khashabi, Jason Weston, Hongyuan Zhan
https://arxiv.org/abs/2510.08240

The Alignment Waltz: Jointly Training Agents to Collaborate for Safety
Harnessing the power of LLMs requires a delicate dance between being helpful and harmless. This creates a fundamental tension between two competing challenges: vulnerability to adversarial attacks that elicit unsafe content, and a tendency for overrefusal on benign but sensitive prompts. Current approaches often navigate this dance with safeguard models that completely reject any content that contains unsafe portions. This approach cuts the music entirely-it may exacerbate overrefusals and fail…

Base Models Know How to Reason, Thinking Models Learn When
Constantin Venhoff, Iv\'an Arcuschin, Philip Torr, Arthur Conmy, Neel Nanda
https://arxiv.org/abs/2510.07364 https…

Base Models Know How to Reason, Thinking Models Learn When
Why do thinking language models like DeepSeek R1 outperform their base counterparts? Despite consistent performance gains, it remains unclear to what extent thinking models learn entirely new reasoning capabilities or repurpose pre-existing base model ones. In this work, we propose a hybrid model where we activate reasoning mechanisms in base models at the right time to elicit thinking-model-level reasoning chains, implying that thinking models exploit already existing capabilities. To ground o…

Unlocking Vision-Language Models for Video Anomaly Detection via Fine-Grained Prompting
Shu Zou, Xinyu Tian, Lukas Wesemann, Fabian Waschkowski, Zhaoyuan Yang, Jing Zhang
https://arxiv.org/abs/2510.02155

Unlocking Vision-Language Models for Video Anomaly Detection via Fine-Grained Prompting
Prompting has emerged as a practical way to adapt frozen vision-language models (VLMs) for video anomaly detection (VAD). Yet, existing prompts are often overly abstract, overlooking the fine-grained human-object interactions or action semantics that define complex anomalies in surveillance videos. We propose ASK-Hint, a structured prompting framework that leverages action-centric knowledge to elicit more accurate and interpretable reasoning from frozen VLMs. Our approach organizes prompts into…

Robust forecast aggregation via additional queries
Rafael Frongillo, Mary Monroe, Eric Neyman, Bo Waggoner
https://arxiv.org/abs/2512.05271 https://arxiv.org/pdf/2512.05271 https://arxiv.org/html/2512.05271
arXiv:2512.05271v1 Announce Type: new
Abstract: We study the problem of robust forecast aggregation: combining expert forecasts with provable accuracy guarantees compared to the best possible aggregation of the underlying information. Prior work shows strong impossibility results, e.g. that even under natural assumptions, no aggregation of the experts' individual forecasts can outperform simply following a random expert (Neyman and Roughgarden, 2022).
In this paper, we introduce a more general framework that allows the principal to elicit richer information from experts through structured queries. Our framework ensures that experts will truthfully report their underlying beliefs, and also enables us to define notions of complexity over the difficulty of asking these queries. Under a general model of independent but overlapping expert signals, we show that optimal aggregation is achievable in the worst case with each complexity measure bounded above by the number of agents $n$. We further establish tight tradeoffs between accuracy and query complexity: aggregation error decreases linearly with the number of queries, and vanishes when the "order of reasoning" and number of agents relevant to a query is $\omega(\sqrt{n})$. These results demonstrate that modest extensions to the space of expert queries dramatically strengthen the power of robust forecast aggregation. We therefore expect that our new query framework will open up a fruitful line of research in this area.
toXiv_bot_toot

Design and Implementation of a Secure RAG-Enhanced AI Chatbot for Smart Tourism Customer Service: Defending Against Prompt Injection Attacks -- A Case Study of Hsinchu, Taiwan
Yu-Kai Shih, You-Kai Kang
https://arxiv.org/abs/2509.21367

Design and Implementation of a Secure RAG-Enhanced AI Chatbot for Smart Tourism Customer Service: Defending Against Prompt Injection Attacks -- A Case Study of Hsinchu, Taiwan
As smart tourism evolves, AI-powered chatbots have become indispensable for delivering personalized, real-time assistance to travelers while promoting sustainability and efficiency. However, these systems are increasingly vulnerable to prompt injection attacks, where adversaries manipulate inputs to elicit unintended behaviors such as leaking sensitive information or generating harmful content. This paper presents a case study on the design and implementation of a secure retrieval-augmented gen…

More Than One Teacher: Adaptive Multi-Guidance Policy Optimization for Diverse Exploration
Xiaoyang Yuan, Yujuan Ding, Yi Bin, Wenqi Shao, Jinyu Cai, Jingkuan Song, Yang Yang, Hengtao Shen
https://arxiv.org/abs/2510.02227

More Than One Teacher: Adaptive Multi-Guidance Policy Optimization for Diverse Exploration
Reinforcement Learning with Verifiable Rewards (RLVR) is a promising paradigm for enhancing the reasoning ability in Large Language Models (LLMs). However, prevailing methods primarily rely on self-exploration or a single off-policy teacher to elicit long chain-of-thought (LongCoT) reasoning, which may introduce intrinsic model biases and restrict exploration, ultimately limiting reasoning diversity and performance. Drawing inspiration from multi-teacher strategies in knowledge distillation, we…

Efficient and Accessible Discrete Choice Experiments: The DCEtool Package for R
Daniel P\'erez-Troncoso
https://arxiv.org/abs/2509.15326 https://arxiv.…

Efficient and Accessible Discrete Choice Experiments: The DCEtool Package for R
Discrete Choice Experiments (DCEs) are widely used to elicit preferences for products or services by analyzing choices among alternatives described by their attributes. The quality of the insights obtained from a DCE heavily depends on the properties of its experimental design. While early DCEs often relied on linear criteria such as orthogonality, these approaches were later found to be inappropriate for discrete choice models, which are inherently non-linear. As a result, statistically effici…

Relational Dissonance in Human-AI Interactions: The Case of Knowledge Work
Emrecan Gulay, Eleonora Picco, Enrico Glerean, Corinna Coupette
https://arxiv.org/abs/2509.15836 https…

Relational Dissonance in Human-AI Interactions: The Case of Knowledge Work
When AI systems allow human-like communication, they elicit increasingly complex relational responses. Knowledge workers face a particular challenge: They approach these systems as tools while interacting with them in ways that resemble human social interaction. To understand the relational contexts that arise when humans engage with anthropomorphic conversational agents, we need to expand existing human-computer interaction frameworks. Through three workshops with qualitative researchers, we f…

VoiceBBQ: Investigating Effect of Content and Acoustics in Social Bias of Spoken Language Model
Junhyuk Choi, Ro-hoon Oh, Jihwan Seol, Bugeun Kim
https://arxiv.org/abs/2509.21108

VoiceBBQ: Investigating Effect of Content and Acoustics in Social Bias of Spoken Language Model
We introduce VoiceBBQ, a spoken extension of the BBQ (Bias Benchmark for Question Answering) - a dataset that measures social bias by presenting ambiguous or disambiguated contexts followed by questions that may elicit stereotypical responses. Due to the nature of speech, social bias in Spoken Language Models (SLMs) can emerge from two distinct sources: 1) content aspect and 2) acoustic aspect. The dataset converts every BBQ context into controlled voice conditions, enabling per-axis accuracy, …

SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines
Yizhou Wang, Chen Tang, Han Deng, Jiabei Xiao, Jiaqi Liu, Jianyu Wu, Jun Yao, Pengze Li, Encheng Su, Lintao Wang, Guohang Zhuang, Yuchen Ren, Ben Fei, Ming Hu, Xin Chen, Dongzhan Zhou, Junjun He, Xiangyu Yue, Zhenfei Yin, Jiamin Wu, Qihao Zheng, Yuhao Zhou, Huihui Xu, Chenglong Ma, Yan Lu, Wenlong Zhang, Chunfeng Song, Philip Torr, Shixiang Tang, Xinzhu Ma, Wanli Ouyang, Lei Bai

SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines
We present a scientific reasoning foundation model that aligns natural language with heterogeneous scientific representations. The model is pretrained on a 206B-token corpus spanning scientific text, pure sequences, and sequence-text pairs, then aligned via SFT on 40M instructions, annealed cold-start bootstrapping to elicit long-form chain-of-thought, and reinforcement learning with task-specific reward shaping, which instills deliberate scientific reasoning. It supports four capability famili…