Budget-safe evaluation method speeds up large language model tests
Dynamic Budget Allocation for LLM Evaluation under Hard Resource Constraints
Machine Learning
Summary
Testing large language models often takes a lot of computing time and resources, especially when waiting for rare events to happen during interactions. The authors developed a new method called HARP that carefully manages a fixed computational budget so evaluations never run out of resources mid-way. HARP adapts how much time to spend on each interaction and still provides guaranteed reliable results about model performance. Their tests showed that HARP keeps costs under control and produces stable, unbiased measurements for things like safety checks and task success.
What this means in practice
- •For ai safety teams: Efficiently test LLM safety by reliably measuring jailbreak and toxic output rates within strict compute budgets.
- •For llm deployment engineers: Control computational costs precisely while evaluating multi-step model behaviors for agentic tasks and hallucination detection.
Authors
Shai Feldman, Yaniv Romano
Abstract
We evaluate large language models (LLMs) in multi-turn interactions through their time-to-event: the number of interaction steps required to produce an event of interest, such as a successful jailbreak or agentic task completion. Under limited compute, interactions may be terminated before the event occurs, so that event times are only partially observed (censored). Existing allocation methods for calibrating time-to-event bounds satisfy the budget only in expectation and can exceed the available budget on a particular evaluation run. Enforcing a hard constraint is particularly challenging as the cost of a trajectory is initially unknown. We introduce Hard-budget Allocation with Reflow for Predictive calibration (HARP), a budget allocation that satisfies hard resource constraints and adaptively reallocates unused budget. We show how to use HARP to construct lower predictive bounds (LPBs) on the time-to-event and to estimate evaluation metrics such as the jailbreak rate on a fixed benchmark. Although HARP induces dependence in acquisition decisions across different trajectories, we prove that HARP never exceeds the target budget, that its LPBs have finite-sample coverage guarantees, and that its metric estimates are unbiased. Experiments on agentic task success, LLM jailbreaks, toxic content generation, and RAG hallucinations show that HARP achieves coverage close to the nominal level with low variance, while never exceeding the given budget.