9 papers
Revisiting Energy-based Tabular Anomaly Detection: Energy and Reconstruction are Complementary
Junichiro Niimi
Tabular anomaly detection is dominated by classical density-proxy methods (Isolation Forest, OCSVM, LOF), reconstruction-based detectors (Autoencoders, VAEs), and modern non-parame…
Three-in-One World Model: Energy-Based Consistency, Prediction, and Counterfactual Inference for Marketing Intervention
Junichiro Niimi
Marketing decisions reflect the interaction of latent consumer heterogeneity, time-varying internal states, and explicit interventions, a structure that current prediction- and lan…
Hierarchical Memorization in Large Language Models: Evidence from Citation Generation
Junichiro Niimi
Large language models (LLMs) generate fluent text across a wide range of tasks, but the fabrication of non-existent academic citations remains a critical and well-documented failur…
The Mouth is Not the Brain: Bridging Energy-Based World Models and Language Generation
Junichiro Niimi
Large Language Models (LLMs) generate fluent text, yet whether they truly understand the world or merely produce plausible texts about it remains contested. We propose an architect…
Distortion Instead of Hallucination: The Effect of Reasoning Under Strict Constraints
Junichiro Niimi
With the widespread adoption of large language models (LLMs), hallucinations, which are non-factual fabrications in model outputs, have become serious concerns. Reasoning capabilit…
Hallucinations in Bibliographic Recommendation: Citation Frequency as a Proxy for Training Data Redundancy
Junichiro Niimi
Large language models (LLMs) have been increasingly applied to a wide range of tasks, from natural language understanding to code generation. While they have also been used to assi…