Calibration-gated LLM pseudo-observations reduce cumulative regret by 19% versus pure LinUCB on a 5-arm news recommendation task when using task-specific prompts, but generic prompts increase regret on both tested environments.
Efficient sequential decision making with large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Calibration-Gated LLM Pseudo-Observations for Online Contextual Bandits
Calibration-gated LLM pseudo-observations reduce cumulative regret by 19% versus pure LinUCB on a 5-arm news recommendation task when using task-specific prompts, but generic prompts increase regret on both tested environments.