LLMs
Latest breakthroughs in Large Language Models
Articles
Fine-Grained Emotion Classification from Mobile App Reviews: A⭐9
This 2026 empirical study compares encoder-only fine-tuning with decoder-only LLM prompting for fine-grained multi-label emotion classification of mobile app re...
Training Numerical Intelligence via Auto-Diagnosis and Skill Discovery⭐8
ADSD links numerical diagnosis to reusable solver skills, improving accuracy, robustness, and efficiency across power flow, ODEs, and PDEs.
HakemBench: A Turkish Benchmark of Typed Decisions for LLM Evaluation⭐8
HakemBench introduces a Turkish benchmark of 2,346 items for evaluating LLM probabilistic decisions across seven tracks using calibration-aware metrics and boot...
MintFlow: Training-Free Minimal Trajectory Intervention for⭐8
MintFlow introduces a training-free constrained sampling method that minimally perturbs pretrained flow matching trajectories, enforcing constraints without ret...
The First Token Is Not the Verdict: Hidden Costs of Reading LLM⭐8
Reading LLM judge verdicts from the first token overstates position bias by up to 42 points, per new research—a hidden cost for anyone auditing judge reliabilit...
SCM-Based Fairness and Faithful Explainability for Legal⭐8
SCM-based debiasing of LegalBERT fails to reduce gender disparity yet consistently degrades SHAP explanation faithfulness across five seeds, revealing a dissoci...
From Proposal to Verified Effect: Praxa, an Evidence-Bound⭐9
Praxa presents an evidence-bound harness for governed AI agent execution, with explicit state tracking, audit results, and pilot benchmarks from proposal to ver...
When Do Causal World Models Help Modular LLM Agents⭐8
Causal world models improve modular LLM agents most in structured tool environments where cross-module interfaces are identifiable and decision-relevant at acti...
On-Device Named-Entity Recognition: A Deployability Study of⭐9
A deployability study of on-device named-entity recognition across nine systems, evaluating accuracy, latency, output validity, and the trustworthiness of model...
Heavy-Tailed Memory Traces in Long-Horizon Language Agents⭐9
Long-horizon language agents show heavy-tailed memory traces. This study introduces CTWM, a rank-based memory controller that cuts tail prediction error and tok...