English
Related papers

Related papers: When and How Human Curation Backfires: Preference …

200 papers

As synthetic data proliferates across the Internet, it is often reused to train successive generations of generative models. This creates a ``self-consuming loop" that can lead to training instability or \textit{model collapse}. Common…

Machine Learning · Computer Science 2025-11-18 Zhongteng Cai , Yaxuan Wang , Yang Liu , Xueru Zhang

Large language models have the potential to generate explanations for their own predictions in a variety of styles based on user instructions. Recent research has examined whether these self-explanations faithfully reflect the models'…

Computation and Language · Computer Science 2025-12-09 Tomoki Doi , Masaru Isonuma , Hitomi Yanaka

Linearly transforming stimulus representations of deep neural networks yields high-performing models of behavioral and neural responses to complex stimuli. But does the test accuracy of such predictions identify genuine representational…

Neurons and Cognition · Quantitative Biology 2026-01-05 Itamar Avitan , Tal Golan

Widespread deployment of societal-scale machine learning systems necessitates a thorough understanding of the resulting long-term effects these systems have on their environment, including loss of trustworthiness, bias amplification, and…

Machine Learning · Computer Science 2024-05-07 Andrey Veprikov , Alexander Afanasiev , Anton Khritankov

Personalized adaptation technology has been adopted in a wide range of digital applications such as health, training and education, e-commerce and entertainment. Personalization systems typically build a user model, aiming to characterize…

Human-Computer Interaction · Computer Science 2021-03-03 Santiago Ontañón , Jichen Zhu

What we discover and see online, and consequently our opinions and decisions, are becoming increasingly affected by automated machine learned predictions. Similarly, the predictive accuracy of learning machines heavily depends on the…

Information Retrieval · Computer Science 2020-01-15 Sami Khenissi , Olfa Nasraoui

Calibration has been proposed as a way to enhance the reliability and adoption of machine learning classifiers. We study a particular aspect of this proposal: how does calibrating a classification model affect the decisions made by…

Human-Computer Interaction · Computer Science 2025-08-27 Meir Nizri , Amos Azaria , Chirag Gupta , Noam Hazon

The problem of model collapse has presented new challenges in iterative training of generative models, where such training with synthetic data leads to an overall degradation of performance. This paper looks at the problem from a…

Machine Learning · Statistics 2026-02-19 Soham Bakshi , Sunrit Chakraborty

The alignment problem refers to concerns regarding powerful intelligences, ensuring compatibility with human preferences and values as capabilities increase. Current large language models (LLMs) show misaligned behaviors, such as strategic…

Computation and Language · Computer Science 2026-03-10 Roshni Lulla , Fiona Collins , Sanaya Parekh , Thilo Hagendorff , Jonas Kaplan

Today's computer vision models achieve human or near-human level performance across a wide variety of vision tasks. However, their architectures, data, and learning algorithms differ in numerous ways from those that give rise to human…

Computer Vision and Pattern Recognition · Computer Science 2025-02-18 Lukas Muttenthaler , Jonas Dippel , Lorenz Linhardt , Robert A. Vandermeulen , Simon Kornblith

Reward-model-based fine-tuning is a central paradigm in aligning Large Language Models with human preferences. However, such approaches critically rely on the assumption that proxy reward models accurately reflect intended supervision, a…

Computation and Language · Computer Science 2026-01-21 Zixuan Liu , Siavash H. Khajavi , Guangkai Jiang , Xinru Liu

Pretraining corpora contain extensive discourse about AI systems, yet the causal influence of this discourse on downstream alignment remains poorly understood. If prevailing descriptions of AI behaviour are predominantly negative, LLMs may…

Computation and Language · Computer Science 2026-02-23 Cameron Tice , Puria Radmard , Samuel Ratnam , Andy Kim , David Africa , Kyle O'Brien

In real-world environments, autonomous agents rely on their egocentric observations. They must learn adaptive strategies to interact with others who possess mixed motivations, discernible only through visible cues. Several Multi-Agent…

Multiagent Systems · Computer Science 2023-12-15 Violet Xiang , Logan Cross , Jan-Philipp Fränken , Nick Haber

In robot-assisted therapy for individuals with Autism Spectrum Disorder, the workload of therapists during a therapeutic session is increased if they have to control the robot manually. To allow therapists to focus on the interaction with…

Robotics · Computer Science 2022-07-26 Michał Stolarz , Alex Mitrevski , Mohammad Wasil , Paul G. Plöger

Recent successes of reinforcement learning (RL) in training large reasoning models motivate the question of whether self-training - the process where a model learns from its own judgments - can be sustained within RL. In this work, we study…

Machine Learning · Computer Science 2025-10-10 Sheikh Shafayat , Fahim Tajwar , Ruslan Salakhutdinov , Jeff Schneider , Andrea Zanette

Mixed-initiative systems allow users to interactively provide feedback to potentially improve system performance. Human feedback can correct model errors and update model parameters to dynamically adapt to changing data. Additionally, many…

Human-Computer Interaction · Computer Science 2020-08-31 Donald R. Honeycutt , Mahsan Nourani , Eric D. Ragan

In many economically relevant contexts where machine learning is deployed, multiple platforms obtain data from the same pool of users, each of whom selects the platform that best serves them. Prior work in this setting focuses exclusively…

Machine Learning · Computer Science 2026-03-02 Adhyyan Narang , Sarah Dean , Lillian J Ratliff , Maryam Fazel

Curriculum learning, a training technique where data is presented to the model in order of example difficulty (e.g., from simpler to more complex documents), has shown limited success for pre-training language models. In this work, we…

Computation and Language · Computer Science 2025-09-29 Loris Schoenegger , Lukas Thoma , Terra Blevins , Benjamin Roth

Designing recommendation systems that serve content aligned with time varying preferences requires proper accounting of the feedback effects of recommendations on human behavior and psychological condition. We argue that modeling the…

Information Retrieval · Computer Science 2022-08-09 Mihaela Curmei , Andreas Haupt , Dylan Hadfield-Menell , Benjamin Recht

The recent phenomenal success of language models has reinvigorated machine learning research, and large sequence models such as transformers are being applied to a variety of domains. One important problem class that has remained relatively…