arXiv ·
CME-SpectrumBench: Can LLMs Analyze Condensed Matter Spectral Data?
Public paper from arXiv. Open the source to read the full record.
Home / Browse
Models & research
Examine models, papers and evaluations with their methods and limitations.
802 public stories
arXiv ·
The Judge Can Debias Itself: Awareness and Self-Debiasing for Reliable LLM-as-a-Judge
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Continuous Ontology Assurance through External Resources -- An Ontology Engineering Method with a Case Study in Software Language Engineering
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Screening LLM Judges Without Ground Truth: A Preliminary Evaluation of an AI Dental Hygiene Coach
Public paper from arXiv. Open the source to read the full record.
arXiv ·
FlashRT-PAI: Fast Kernels Are Not Fast Pipelines for Physical AI Inference
Public paper from arXiv. Open the source to read the full record.
Hacker News ·
Should agent-memory benchmarks test stale information?
Hacker News recorded 2 points and 0 comments as of Oct 20, 2026 (UTC).
Hacker News ·
Profiling the Attack Surface of AI Agent Skills
Hacker News recorded 1 points and 0 comments as of Oct 20, 2026 (UTC).
Hacker News ·
Scope: Open-source evaluation for AI coding agents
Hacker News recorded 2 points and 0 comments as of Oct 20, 2026 (UTC).
TechCrunch ·
Tenstorrent hits $6.2B valuation to scale open-weight AI chips
Public article from TechCrunch. Open the source to read the full record.
MIT News ·
Why teaching AI about symmetry could make prenatal diagnosis more reliable
A model developed by researchers at MIT and Boston Children's Hospital adjusts scans on the fly to track fetal movement, potentially sparing families repeat hospital visits.
arXiv ·
Embeddings Are Overpriced? A Frozen 16 MB Vocabulary for Small and Ternary Language Models
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Where Prefill Expert Reduction Hurts MoE Models: A Few Prompt Tokens Carry Most of the Short-Answer F1 Loss
Public paper from arXiv. Open the source to read the full record.
arXiv ·
From Parallels to Divergence: Language Models' Learning of Action Nominal Constructions
Public paper from arXiv. Open the source to read the full record.
arXiv ·
RealCLI: Toward a Unified Evaluation of Human-Agent Collaboration for CLI Agents
Public paper from arXiv. Open the source to read the full record.
arXiv ·
AuditKIT: A Unified Evaluation Spine for Benchmarking, Judging, and Comparing Large Language Models and Agentic Systems
Public paper from arXiv. Open the source to read the full record.
arXiv ·
alkhder at ImageEval 2026 Shared Tasks: Constrained Selection and Rotation-Averaged Logit Scoring for Multimodal Hallucination Detection
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Learning User Representations to Improve Simulation Fidelity
Public paper from arXiv. Open the source to read the full record.
arXiv ·
alkhder at AlexandriaX-2026: Context-Aware English-to-Dialectal Arabic Dialogue Translation with QLoRA-Fine-Tuned NileChat-3B
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Literal Lock-In: How Test Language Shifts Literal Attraction in Typed Decision Models on Bengali Idioms
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Pearl-Chat: Engineering a native Luganda language model from first principles in JAX and Flax NNX
Public paper from arXiv. Open the source to read the full record.
arXiv ·
HeRE: A Novel Benchmark for Hebrew Relation Extraction via LLM-Guided Denoising of Knowledge Graph Alignments
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Cultural (In)Competence: Investigating Culture-Specific Stereotype Detection Capabilities of LLMs
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Who Do Perspectivist Models Predict Well? Annotator Agreement, Sparsity, and Performance
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Mitigating Demographic Disparities in Explanation-Human Alignment via Rationale Regularization
Public paper from arXiv. Open the source to read the full record.
arXiv ·
SAG2: Embedding-Free Multi-Hop Retrieval with BM25 and JEV
Public paper from arXiv. Open the source to read the full record.
arXiv ·
The Model Knows Better: Defending Medical Multi-Agent Systems Against Prompt Injection
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Broad and Efficient PII Detection with Unified Labels
Public paper from arXiv. Open the source to read the full record.
arXiv ·
When Does Uncertainty Measure RAG Hallucination Risk?
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Trajectory-Guided Steering: Mitigating Spurious Feature Bias in Clinical Classification
Public paper from arXiv. Open the source to read the full record.
arXiv ·
A Plausible Explanation Is Enough to Mislead Multimodal Judges
Public paper from arXiv. Open the source to read the full record.