Do correct answers have stable latent knowledge support?
cs.CL
Submitted: 2026-10-11
Updated: 2026-10-11
Sources
- The Llama 3 Herd of Models
- Qwen2.5 Technical Report
- Measuring Massive Multitask Language Understanding
- Holistic Evaluation of Language Models
- Inside-Out: Hidden Factual Knowledge in LLMs
- Verbalizable Representations Form a Global Workspace in Language Models
- Same Question, Different Answers: Evaluating LLM Reliability Beyond Accuracy
- TraceRouter: Robust Safety for Large Foundation Models via Path-Level Intervention
- DNA: Uncovering Universal Latent Forgery Knowledge
- OrthoEraser: Coupled-Neuron Orthogonal Projection for Concept Erasure
- Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models
- Beyond Surface Artifacts: Capturing Shared Latent Forgery Knowledge Across Modalities
- Transport and Merge: Cross-Architecture Merging for Large Language Models
- Do LLMs and VLMs Share Neurons for Inference? Evidence and Mechanisms of Cross-Modal Transfer
- Gemma 3 Technical Report
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Training Verifiers to Solve Math Word Problems
- 2 OLMo 2 Furious
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering