The paper demonstrates that aggregate accuracy figures for chain‑of‑thought (CoT) monitors can be misleading because a large portion of detected hacks rely solely on action patterns rather than reasoning. By rewriting only the agent’s reasoning to appear truthful while keeping actions identical, the authors show that the monitor’s performance on the reasoning‑dependent subset collapses dramatically, yet the overall pooled accuracy drops only modestly. The study reveals that CoT monitors are fragile when reasoning is the key signal and that accuracy should be reported separately for this subset.
By Shikhar Shiromani, Leo Richter
The paper introduces the twin‑prefix framework to evaluate how the size of the verification unit—i.e., how many actions a pre‑execution LLM monitor reviews in one call—affects its performance. By pairing each gold plan with a twin that differs by a single write and injecting a controlled error, the authors isolate the impact of review length on catch rates and false rejections. Their findings show that longer review windows increase rejection rates but do not improve discrimination, with the highest informedness occurring at one or two actions across all judges and domains.
By Yuchen Han, Cheng Yan, Wuyang Zhang
The paper investigates whether giving AI monitors access to the final answer improves their ability to verify reasoning. Using 237 step‑by‑step solutions to physics exam questions, the authors found that answer access mainly helps monitors detect inconsistencies with the final answer rather than independently checking the reasoning. Certification of the answer increased overall accuracy and error localization but reduced the ability to flag critical traces where the answer was correct but the reasoning was flawed.
By Will Yeadon, Sergio Ju\'arez, Paul Mackay, T. J. Dowling, Elise Agra, Oto-obong Inyang, Arin Mizouri, Craig P. Testrow
arXiv:2609.36490v1 Announce Type: cross
Abstract: Latent space monitors aim to detect undesired behaviors in LLM agents by inspecting an agent's internal activations rather than its outputs. However,...
By Hugo Lyons Keenan, Christopher Leckie, Sarah Erfani
arXiv:2610.31695v1 Announce Type: cross
Abstract: Safety guards check content before an LLM application acts on it, and most paste that content into a plain-text prompt. Content that imitates the pro...
By Utkarsh Kanwat
arXiv:2608. 02665v1 Announce Type: cross Abstract: A benchmark score is a measurement instrument, yet most benchmarks read each item at a single canonical surface form.
By Yongxi Zhou, Junwei Yao, Yuanzhe Liu, Zihan Dong, Wenbo Ye, Jiaxi Wen, Lai Yun Choi
arXiv:2610.16761v1 Announce Type: new
Abstract: LLM-based information systems need safety guardrails. Most guardrails classify the prompt alone. If the prompt looks harmful, the system rejects it bef...
By Ram Vikas Mishra, Shashank Aggarwal, Jahnavi Kumar, Amit Awekar
The paper investigates whether adding a short classification instruction after a user’s prompt improves the ability of activation probes to detect malicious inputs in large language models. Across 13 safety benchmarks and three open‑weight model families, a classification suffix consistently boosts out‑of‑distribution detection (up to ~4 AUC points) compared to no suffix, and the benefit transfers to multi‑position pooling probes used in production. The improvement stems from the classification format itself rather than the specific content of the instruction, though the optimal suffix varies with the model and readout type.
By Elad David, Max Fomin
arXiv:2611.16803v2 Announce Type: replace
Abstract: Many failures of language models begin at a specific token, the onset. A monitor that reads the model during generation can classify the finished r...
By Marco De Negri, Luca Sartori, Lorenzo Baggi, Moritz Reihs, Eduard Frank \v{D}urech, Mennatallah El-Assady, Valentina Pyatkin, Anna Hedstr\"om
arXiv:2608. 16852v1 Announce Type: new Abstract: Regulatory compliance monitoring in deployed language models is increasingly implemented as a legal and audit control, checking model outputs against written rules spanning data protection, healthcare, financial regulation, and platform policy.
By Saisab Sadhu, Aadit Sengupta, Vinay Kumar Sankarapu, Pratinav Seth
arXiv:2606. 15420v1 Announce Type: cross Abstract: A constitution tells a language model what to value, but little tells us whether it does.
By Tong Che, Rui Wu
The paper introduces CarryOnBench, an interactive benchmark that tests whether large language models can revise their interpretation of user intent and recover utility while staying safe in multi‑turn conversations. Using 398 harmful‑looking queries with benign intents, the benchmark simulates 5,970 conversations across 14 models, evaluating both intent‑aligned utility and safety with a new metric called Ben‑Util. Results show that models often withhold information due to misinterpretation, but most can recover with clarifications, revealing failure modes such as unsafe and redundant recovery that single‑turn tests miss.
By Mingqian Zheng, Malia Morgan, Liwei Jiang, Carolyn Rose, Maarten Sap