{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/detecting-high-stakes-interactions-with","title":"Detecting High-Stakes Interactions with Activation Probes","arxiv_id":"2506.10805","date":"2025-06-12","proceeding":null,"authors":["Alex McKenzie","Urja Pawar","Phil Blandfort","William Bankes","David Krueger","Ekdeep Singh Lubana","Dmitrii Krasheninnikov"],"abstract":"Monitoring is an important aspect of safely deploying Large Language Models (LLMs). This paper examines activation probes for detecting \"high-stakes\" interactions -- where the text indicates that the interaction might lead to significant harm -- as a critical, yet underexplored, target for such monitoring. We evaluate several probe architectures trained on synthetic data, and find them to exhibit robust generalization to diverse, out-of-distribution, real-world data. Probes' performance is comparable to that of prompted or finetuned medium-sized LLM monitors, while offering computational savings of six orders-of-magnitude. Our experiments also highlight the potential of building resource-aware hierarchical monitoring systems, where probes serve as an efficient initial filter and flag cases for more expensive downstream analysis. We release our novel synthetic dataset and codebase to encourage further study.","url_abs":"https://arxiv.org/abs/2506.10805v1","url_pdf":"https://arxiv.org/pdf/2506.10805v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2506.10805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.10805"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/arrrlex/models-under-pressure","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"found_in_text":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"5989c8364e7f2c4e","entry":"inv_softmax","repo":"arrrlex/models-under-pressure","repo_kind":"found_in_text","path":"src/models_under_pressure/experiments/evaluate_probes.py","file_url":"https://github.com/arrrlex/models-under-pressure/blob/HEAD/src/models_under_pressure/experiments/evaluate_probes.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5989c8364e7f2c4e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}