Similar Items: Inducing Artificial Uncertainty in Language Models
- Implicit Representations of Grammaticality in Language Models
- Geometry-Calibrated Conformal Abstention for Language Models
- The Frequency Confound in Language-Model Surprisal and Metaphor Novelty
- Beyond Decodability: Reconstructing Language Model Representations with an Encoding Probe
- The Counterexample Game: Iterated Conceptual Analysis and Repair in Language Models
- Scalable Token-Level Hallucination Detection in Large Language Models