When Policies Change Probabilities: Modular Decision-Making for LLM Code Review
Source
arxiv.org
Author
Rasvik Kudum, Max Corbett, Hitansh Paliwal, Romaisa Fatima, Thomas Jiralerspong, Sneheel Sarangi
Date
Why it matters
embeddingA list of numbers representing a piece of text's meaning, so that similar meanings end up numerically close and can be searched.Full definition → cost-sensitive approval policies directly in a risk-estimation prompt can corrupt the reported probabilities themselves, sometimes making decisions worse than a blanket rejection under high-cost settings; separating probability elicitation from policy and using an independent monitor score improves calibrationHow well a model's confidence matches reality — a calibrated model saying "90% sure" is right about 90% of the time.Full definition → and reduces loss.
Key takeaways · AI-distilled
Across 15,792 responses on 720 patches, telling a reviewer the cost of mistakes changes its reported failure probabilities by 13.6-16.9 points on identical evidence - the policy corrupts the estimate it is supposed to consume.
Under a 10:1 false-accept cost prompt, every one of the four deployed reviewers returns actions WORSE than rejecting all patches outright.
Applying the same high-cost rule to probabilities elicited WITHOUT policy information reduces loss for all four systems - proof the elicitation step itself, not just the decision rule, contributes the excess loss.
Their modular pipeline (policy-blind risk elicitation + independent monitor score + costs applied in code) cuts mean loss by .073 per issue at equal costs while accepting 58-68% of patches.
Practical rule: evaluate risk, outside evidence and action separately - never let the downstream policy leak into the probability prompt.
Terms in this piece · Glossary
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
embedding — A list of numbers representing a piece of text's meaning, so that similar meanings end up numerically close and can be searched.
calibration — How well a model's confidence matches reality — a calibrated model saying "90% sure" is right about 90% of the time.
Key quotes
“A probability should depend on evidence; costs should determine the action taken from it.”
“For every reviewer, the actions returned under the high-cost prompt are worse than rejecting all patches.”
“Downstream policy can therefore change the probability it is meant to use, motivating separate evaluation of risk, outside evidence, and action.”
