Featured Papers
Popular high-signal papers with direct links to full protocol pages.
- Implicit Representations of Grammaticality in Language Models
May 6, 2026 · Citations: 0
Grammaticality and likelihood are distinct notions in human language.
- MRI-Eval: A Tiered Benchmark for Evaluating LLM Performance on MRI Physics and GE Scanner Operations Knowledge
May 6, 2026 · Citations: 0
Background: Existing MRI LLM benchmarks rely mainly on review-book multiple-choice questions, where top proprietary models already score highly, limiting discrimination.
- The First Token Knows: Single-Decode Confidence for Hallucination Detection
May 6, 2026 · Citations: 0
Across three 7-8B instruction-tuned models and two benchmarks, phi_first achieves a mean AUROC of 0.820, compared with 0.793 for semantic agreement and 0.791 for standard surface-form self-consistency.
- PSK at SemEval-2026 Task 9: Multilingual Polarization Detection Using Ensemble Gemma Models with Synthetic Data Augmentation
May 6, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Beyond Semantics: An Evidential Reasoning-Aware Multi-View Learning Framework for Trustworthy Mental Health Prediction
May 6, 2026 · Citations: 0
Benchmarking on three real-world datasets, Dreaddit, SDCNL, and DepSeverity, reports accuracies of 0.835, 0.731, and 0.751, respectively, demonstrating its potential for reliable mental health prediction.
- Text Corpora as Concept Fields: Black-Box Hallucination and Novelty Measurement
May 6, 2026 · Citations: 0
Concept Fields provide a fast, lightweight, and interpretable signal for groundedness and novelty, complementary to LLM-as-judge and white-box detectors.
- Continual Knowledge Updating in LLM Systems: Learning Through Multi-Timescale Memory Dynamics
May 6, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Automatically Finding and Validating Unexpected Side-Effects of Interventions on Language Models
May 6, 2026 · Citations: 0
We present an automated, contrastive evaluation pipeline for auditing the behavioral impact of interventions on large language models.
- The Pinocchio Dimension: Phenomenality of Experience as the Primary Axis of LLM Psychometric Differences
May 6, 2026 · Citations: 0
To test this hypothesis at the item level, we introduce the Pinocchio score (π_i), the ratio of inter-model response variance under neutral prompting to that under a human-simulation prompt, as an annotation-free measure of each item's…
- The Impossibility Triangle of Long-Context Modeling
May 6, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- When Relations Break: Analyzing Relation Hallucination in Vision-Language Model Under Rotation and Noise
May 6, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Detecting Hallucinations in Large Language Models via Internal Attention Divergence Signals
May 6, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.