Related papers: Post-Selections in AI and How to Avoid Them

Positive and Unlabeled (PU) learning, a binary classification model trained with only positive and unlabeled data, generally suffers from overfitted risk estimation due to inconsistent data distributions. To address this, we introduce a…

The reliability of controlled experiments, commonly referred to as "A/B tests," is often compromised by network interference, where the outcomes of individual units are influenced by interactions with others. Significant challenges in this…

Boosting is a method for finding a highly accurate hypothesis by linearly combining many ``weak" hypotheses, each of which may be only moderately accurate. Thus, boosting is a method for learning an ensemble of classifiers. While boosting…

Neurosymbolic artificial intelligence is a growing field of research aiming to combine neural network learning capabilities with the reasoning abilities of symbolic systems. Informed multi-label classification is a sub-field of…

The calibration and training of a neural network is a complex and time-consuming procedure that requires significant computational resources to achieve satisfactory results. Key obstacles are a large number of hyperparameters to select and…

The neural plausibility of backpropagation has long been disputed, primarily for its use of non-local weight transport $-$ the biologically dubious requirement that one neuron instantaneously measure the synaptic weights of another. Until…

Our goal is to understand how post-training methods, such as fine-tuning, alignment, and unlearning, modify language model behavior and representations. We are particularly interested in the brittle nature of these modifications that makes…

Large-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved great success and become a milestone in the field of artificial intelligence (AI). Owing to sophisticated pre-training objectives and huge model parameters,…

Recent releases of Large Language Models (LLMs), e.g. ChatGPT, are astonishing at generating human-like texts, but they may impact the authenticity of texts. Previous works proposed methods to detect these AI-generated texts, including…

Pseudo Artificial Intelligence bias (PAIB) is broadly disseminated in the literature, which can result in unnecessary AI fear in society, exacerbate the enduring inequities and disparities in access to and sharing the benefits of AI…

The discourse on risks from advanced AI systems ("AIs") typically focuses on misuse, accidents and loss of control, but the question of AIs' moral status could have negative impacts which are of comparable significance and could be realised…

As with any task, the process of building machine learning models can benefit from prior experience. Meta-learning for classifier selection leverages knowledge about the characteristics of different datasets and/or the past performance of…

AI is powerful, but it can make choices that result in objective errors, contextually inappropriate outputs, and disliked options. We need AI-resilient interfaces that help people be resilient to the AI choices that are not right, or not…

This paper investigates the voting behaviors of Large Language Models (LLMs), specifically GPT-4 and LLaMA-2, their biases, and how they align with human voting patterns. Our methodology involved using a dataset from a human voting…

Deep neural networks achieve remarkable performances on a wide range of tasks with the aid of large-scale labeled datasets. Yet these datasets are time-consuming and labor-exhaustive to obtain on realistic tasks. To mitigate the requirement…

Artificial Intelligence systems require a through assessment of different pillars of trust, namely, fairness, interpretability, data and model privacy, reliability (safety) and robustness against against adversarial attacks. While these…

Ramaswamy et al. reported in Nature Medicine that ChatGPT Health under-triages 51.6% of emergencies, concluding that consumer-facing AI triage poses safety risks. However, their evaluation used an exam-style protocol -- forced A/B/C/D…

Prior work has shown that language models can be tuned to follow user instructions using only a small set of high-quality instructions. This has accelerated the development of methods that filter a large, noisy instruction-tuning datasets…

Large language models (LLMs) are increasingly used as epistemic partners in everyday reasoning, yet their errors remain predominantly analyzed through predictive metrics rather than through their interpretive effects on human judgment. This…

Testing of deep learning models is challenging due to the excessive number and complexity of computations involved. As a result, test data selection is performed manually and in an ad hoc way. This raises the question of how we can…