Papers for
ai monitoring teams
Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.
Large language model audits clinical prediction models with high accuracy
Auditing black-box clinical prediction models with a large language model through queries alone: a blinded test with planted flaws
Abstract: Large language models (LLMs) are used to explain clinical prediction models, on the promise that they can say what a model computes, find its faults and even reveal new knowledge in it. We tested the three promises where the answers could be checked. From the International Stroke Trial we trained four kinds of model (logistic regression, explainable boosting machine, gradient-boosted trees, neural network) for two outcomes on patients randomised earlier, planted one flaw in each of 24 copies (an under-predicted subgroup, a reversed risk factor or an implausible step) and mixed them with the 8 clean models. GPT-6 Astra audited each model three times, blind, through a tool that only returned the model's predictions; the judging rules were committed before any run and applied by program. Its surrogate models, with a median of 128 terms, reproduced the audited models' log-odds with a mean $R^2$ of 0.976 (0.959 for an additive surrogate of 42 terms fitted by an analyst). It found the planted flaw in 69 of 72 runs (96%; 95% CI 80% to 99%); a script written for the purpose found all 24. It also reported many more problems: 60% of 1,089 checkable reports failed the pre-specified check against the model's average behaviour; post hoc, most of these were real but small steps, and 15% of the checkable reports were not found in the model. Of 601 unexpected relationships it read out of the clean models, 11% held in patients randomised later (random pairs 6%; a regression scan's shorter list of its strongest candidates, 28%); after a check on the training data, 33% against 30%. With query access alone, an LLM can describe a black-box model faithfully and find nearly every planted flaw, as a purpose-written script also did; its reports of problems must be checked on the model and its discoveries on data.
Task difficulty drives failure prediction more than run-level signals
Disentangling Task Difficulty from Run-Level Failure in Agent Failure Prediction
Abstract: Predicting whether an LLM agent will fail has emerged as a promising direction for supporting intervention during execution. Recent approaches report strong predictive performance, often with AUROC values between 0.85 and 0.94. However, predictors are typically trained by pooling runs from many tasks. We hypothesize that part of this performance comes from recognizing that some tasks are harder than others, rather than detecting whether a particular run is heading toward failure. This distinction matters because task-level difficulty supports decisions about where to allocate computation, while run-level prediction is needed to decide whether to intervene in an ongoing trajectory. We study benchmarks with repeated attempts of the same task by the same agent and separate cross-unit comparisons from comparisons between successful and failed runs of the same model-task unit. Across the evaluated corpora, more than 99.93% of the positive-negative pairs underlying pooled AUROC are cross-unit. Accordingly, predictors that never observe the current run can achieve high pooled performance, including a difficulty oracle with AUROC up to 0.945, while remaining at chance within task. Early run-level discrimination is consistently weak across trajectory predictors, released monitors, and hidden-state probes, although it improves later in execution and is stronger for weaker agents. Under fixed token budgets, task-level allocation outperforms abort-only strategies, while early stopping becomes beneficial only when within-task AUROC reaches about 0.84-0.93, far above the 0.50-0.55 range observed for early monitors. These results show that failure prediction should be evaluated not only by outcome accuracy, but by whether the captured signal supports the intended deployment decision.