2 papers
cs.CL2026
Probabilistic Calibration Is a Trainable Capability in Language Models
Davide Baldelli, Sruthi Kuriakose, Maryam Hashemzadeh +2
Language models are increasingly used in settings where outputs should follow an intended distribution, yet their generation probabilities are often poorly calibrated to it. In man…
cs.CY2025
BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format
Roland Pihlakas, Sruthi Susan Kuriakose
Many AI alignment discussions of "runaway optimisation" focus on RL agents: unbounded utility maximisers that over-optimise a proxy objective (e.g., "paperclip maximiser", specific…