AutoMonitor-Bench: Evaluating the Reliability of LLM-Based Misbehavior Monitor

ACL ARR 2026 January Submission8769 Authors

Keywords: Misbehavior of LLM, LLM as a judge, Reliability

Abstract: We introduce AutoMonitor-Bench, the first benchmark designed to systematically evaluate the reliability of LLM-based misbehavior monitors across diverse tasks and failure modes. AutoMonitor-Bench consists of 3,010 carefully annotated test samples spanning question answering, code generation, and reasoning, with paired misbehavior and benign instances. We evaluate monitors using two complementary metrics: Miss Rate (MR) and False Alarm Rate (FAR), capturing failures to detect misbehavior and oversensitivity to benign behavior respectively. Evaluating 12 proprietary and 10 open-source LLMs, we observe substantial variability in monitoring performance and a consistent trade-off between MR and FAR, revealing an inherent safety–utility tension. To further explore the limits of monitor reliability, we construct a large-scale training corpus of 153,581 samples and fine-tune Qwen3-4B-Instruction, to investigate whether training on known, relatively easy-to-construct misbehavior datasets improves monitoring performance on unseen and more implicit misbehaviors. Our results highlight the challenges of reliable, scalable misbehavior monitoring and motivate future work on task-aware designing and training strategies for LLM-based monitors.

Paper Type: Long

Research Area: Resources and Evaluation

Research Area Keywords: AI auditing, LLM as a judge, dataset and benchmark

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Data resources

Languages Studied: English

Submission Number: 8769