supervised-learning

MIITA is a memory-induced inference-time adaptation framework for continual learning with small language models. It stores correction-direction prototypes and applies gated hidden-state adaptation at inference time to mitigate catastrophic forgetting without updating backbone parameters.

This paper investigates the use of large language models (LLMs) and supervised classifiers for depression detection from social media text, proposing a prompt-based embedding method that enhances interpretability. Experiments on multiple datasets show that zero-shot LLMs perform well for binary classification but struggle with fine-grained severity, while supervised models on LLM summary embeddings achieve more consistent performance across multi-class and ordinal tasks.

This paper investigates using supervised learning to build an oracle that decides when to apply the computationally expensive Energetic Reasoning propagator in constraint programming, showing high prediction accuracy and highlighting key design choices.

This paper characterizes the inherent interpretability of linear models vs. single-qubit mixed-state models for binary classification, showing that the quantum model learns a hyperellipsoid instead of a hyperplane, with implications for inductive biases and pedagogy.

Proposes Partially Adjudicated Design-Based Supervised Learning (PA-DSL), a method that corrects noisy human labels using a small set of adjudicated cases to debias automated classifiers, achieving nominal coverage and reducing RMSE by 10-17% in experiments.

This paper consolidates the state of the art in supervised political scaling, investigating whether joint prediction of ideological scales and a middle ground between classification and regression can improve performance.

The paper argues that data-driven machine learning systems, including GPT-5, cannot achieve symbolic-level logical reasoning through scaling alone, due to inherent limitations in distinguishing logical structures from statistical regularities.

This paper proposes a Supervised Reinforcement Learning (SRL) framework for coordinating distributed energy resources, pre-training on demonstration data and fine-tuning with RL to improve sample efficiency and performance.

Introduces NatureBench, a cross-disciplinary benchmark of 90 tasks from Nature papers to test AI coding agents, finding the best agent (Claude Opus 4.7) surpasses SOTA on only 17.8% of tasks and often succeeds by reducing science to supervised ML rather than genuine discovery.

This paper uses layer-wise probing to investigate how wav2vec 2.0 and Whisper encode consonant cluster reduction in African American English, finding that both models distinguish reduced and canonical forms and preserve cues to underlying stops.

This paper models how interactive targeted ads can leak user attribute information through observable interactions, and evaluates Bayesian, supervised, and other attack methods on synthetic data. It also discusses disclosure controls as a defense.

This paper evaluates cross-dataset generalization of supervised ML/DL models and prompted LLMs for automatic Bloom's taxonomy classification of assessment questions, finding that LLMs are more robust across diverse educational contexts.

This paper introduces FormatMix, a multi-format training approach that improves LLM consistency across different answer formats by expanding a subset of training items into multiple equivalent formats, showing that format diversity is key to robustness.

Rich Sutton argues that generative AI trained by supervised learning cannot achieve genuine novelty and quality simultaneously, and that true discovery requires a 'vary, evaluate, select' mechanism found in reinforcement learning rather than pure imitation.

This paper formalizes the concept of Bayes-sufficient representations in supervised learning, defining when a representation retains exactly the information needed for Bayes-optimal prediction under a given loss function. It introduces the Bayes quotient as a canonical loss-dependent object and connects the framework to property elicitation, illustrating distinctions between sufficiency, minimality, and excess retained information through experiments.

This paper proposes Q-align DT, a framework that aligns return-to-go with Q-values to improve controllability and performance in offline reinforcement learning, achieving superior results on D4RL benchmarks.

This paper presents an applied evaluation of foundation models for time series forecasting compared to supervised approaches across four operational domains, and proposes a Complexity Router to selectively assign series to the optimal model class for balancing accuracy and inference cost.

This paper proposes goal-conditioned supervised learning (GCSL) as an offline fine-tuning framework for LLMs, which treats feedback as an explicit goal and trains models via supervised learning with a novel goal formulation and natural-language goal representations. Evaluated on non-toxic generation, code generation, and recommendation, it outperforms standard offline baselines.

This paper investigates whether shallow neural network agents can master the card game Schnapsen using reinforcement learning, outperforming a supervised imitation baseline and achieving competitive results against a strong search-based opponent.

This paper argues that exploration is essential for all learning systems, including supervised learning, and proposes a framework for generalized exploration to drive open-ended learning towards general intelligence.