English
Related papers

Related papers: Harmful Random Utility Models

200 papers

Randomized mechanisms, which map a set of bids to a probability distribution over outcomes rather than a single outcome, are an important but ill-understood area of computational mechanism design. We investigate the role of randomized…

Computer Science and Game Theory · Computer Science 2009-04-17 Patrick Briest , Shuchi Chawla , Robert Kleinberg , S. Matthew Weinberg

Recent advances in large language models (LLMs) have intensified the need to understand and reliably curb their harmful behaviours. We introduce a multidimensional framework for probing and steering harmful content in model internals. For…

Artificial Intelligence · Computer Science 2025-07-30 McNair Shah , Saleena Angeline , Adhitya Rajendra Kumar , Naitik Chheda , Kevin Zhu , Vasu Sharma , Sean O'Brien , Will Cai

From the perspective of content safety issues, alignment has shown to limit large language models' (LLMs) harmful content generation. This intentional method of reinforcing models to not respond to certain user inputs seem to be present in…

Computation and Language · Computer Science 2023-08-28 Aibek Bekbayev , Sungbae Chun , Yerzat Dulat , James Yamazaki

This paper reveals a data bias issue that can severely affect the performance while conducting a machine learning model for malicious URL detection. We describe how such bias can be identified using interpretable machine learning…

Machine Learning · Computer Science 2024-02-12 YunDa Tsai , Cayon Liow , Yin Sheng Siang , Shou-De Lin

Large language models (LLMs) are increasingly integrated into a variety of writing tasks. While these tools can help people by generating ideas or producing higher quality work, like many other AI tools they may risk causing a variety of…

Human-Computer Interaction · Computer Science 2025-03-21 Kowe Kadoma , Danaé Metaxa , Mor Naaman

Digital platforms such as social media and e-commerce websites adopt Recommender Systems to provide value to the user. However, the social consequences deriving from their adoption are still unclear. Many scholars argue that recommenders…

Information Retrieval · Computer Science 2024-09-26 Erica Coppolillo , Simone Mungari , Ettore Ritacco , Francesco Fabbri , Marco Minici , Francesco Bonchi , Giuseppe Manco

Algorithmic recourse provides individuals who receive undesirable outcomes from machine learning systems with minimum-cost improvements to achieve a desirable outcome. However, machine learning models often get updated, so the recourse may…

Machine Learning · Computer Science 2026-04-28 Kshitij Kayastha , Vasilis Gkatzelis , Shahin Jabbari

Penalized estimation can conduct variable selection and parameter estimation simultaneously. The general framework is to minimize a loss function subject to a penalty designed to generate sparse variable selection. The…

Computation · Statistics 2024-01-11 Zhu Wang

Human understanding of randomness and variation is shaped by a number of cognitive biases. Here we relate a lesser-known cognitive bias, the "outcome orientation", to medical questions and describe the harm that the outcome orientation can…

Physics Education · Physics 2017-02-20 Parris Taylor Humphrey , Joanna Masel

Recommender systems have become integral to digital experiences, shaping user interactions and preferences across various platforms. Despite their widespread use, these systems often suffer from algorithmic biases that can lead to unfair…

Information Retrieval · Computer Science 2024-09-12 Yongsu Ahn , Quinn K Wolter , Jonilyn Dick , Janet Dick , Yu-Ru Lin

Personalized recommendations form an important part of today's internet ecosystem, helping artists and creators to reach interested users, and helping users to discover new and engaging content. However, many users today are skeptical of…

Cryptography and Security · Computer Science 2024-01-09 Allegra Laro , Yanqing Chen , Hao He , Babak Aghazadeh

Random utility theory models an agent's preferences on alternatives by drawing a real-valued score on each alternative (typically independently) from a parameterized distribution, and then ranking the alternatives according to scores. A…

Multiagent Systems · Computer Science 2012-11-13 Hossein Azari Soufiani , David C. Parkes , Lirong Xia

A task of interest in machine learning (ML) is that of ascribing explanations to the predictions made by ML models. Furthermore, in domains deemed high risk, the rigor of explanations is paramount. Indeed, incorrect explanations can and…

Artificial Intelligence · Computer Science 2025-07-11 Mohamed Siala , Jordi Planes , Joao Marques-Silva

Invariant Causal Prediction (Peters et al., 2016) is a technique for out-of-distribution generalization which assumes that some aspects of the data distribution vary across the training set but that the underlying causal mechanisms remain…

Machine Learning · Computer Science 2021-03-30 Elan Rosenfeld , Pradeep Ravikumar , Andrej Risteski

Large Language Models (LLMs) have achieved remarkable success across diverse natural language tasks, yet the reward models employed for aligning LLMs often encounter challenges of reward hacking, where the approaches predominantly rely on…

Computation and Language · Computer Science 2026-03-06 Biao Liu , Ning Xu , Junming Yang , Hao Xu , Xin Geng

People tell lies when seeking rewards. Large language models (LLMs) are aligned to human values with reinforcement learning where they get rewards if they satisfy human preference. We find that this also induces dishonesty in helpful and…

Computation and Language · Computer Science 2024-06-06 Youcheng Huang , Jingkun Tang , Duanyu Feng , Zheng Zhang , Wenqiang Lei , Jiancheng Lv , Anthony G. Cohn

Self-evaluation using large language models (LLMs) has proven valuable not only in benchmarking but also methods like reward modeling, constitutional AI, and self-refinement. But new biases are introduced due to the same LLM acting as both…

Computation and Language · Computer Science 2024-04-23 Arjun Panickssery , Samuel R. Bowman , Shi Feng

Inverse reinforcement learning (IRL) attempts to infer human rewards or preferences from observed behavior. Since human planning systematically deviates from rationality, several approaches have been tried to account for specific human…

Artificial Intelligence · Computer Science 2019-01-14 Stuart Armstrong , Sören Mindermann

We characterize those ex-ante restrictions on the random utility model which lead to identification. We first identify a simple class of perturbations which transfer mass from a suitable pair of preferences to the pair formed by swapping…

Theoretical Economics · Economics 2024-08-14 Peter P. Caradonna , Christopher Turansick

In assignment problems, the rank distribution of assigned objects is often used to evaluate match quality. Rank-minimizing (RM) mechanisms directly optimize for average rank. While appealing, a drawback is RM mechanisms are not…

Theoretical Economics · Economics 2024-06-19 Peter Troyan