{"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/weakly-supervised-detection-of-hallucinations","title":"Weakly Supervised Detection of Hallucinations in LLM Activations","arxiv_id":"2312.02798","date":"2023-12-05","proceeding":null,"authors":["Miriam Rateike","Celia Cintas","John Wamburu","Tanya Akumu","Skyler Speakman"],"abstract":"We propose an auditing method to identify whether a large language model (LLM) encodes patterns such as hallucinations in its internal states, which may propagate to downstream tasks. We introduce a weakly supervised auditing technique using a subset scanning approach to detect anomalous patterns in LLM activations from pre-trained models. Importantly, our method does not need knowledge of the type of patterns a-priori. Instead, it relies on a reference dataset devoid of anomalies during testing. Further, our approach enables the identification of pivotal nodes responsible for encoding these patterns, which may offer crucial insights for fine-tuning specific sub-networks for bias mitigation. We introduce two new scanning methods to handle LLM activations for anomalous sentences that may deviate from the expected distribution in either direction. Our results confirm prior findings of BERT's limited internal capacity for encoding hallucinations, while OPT appears capable of encoding hallucination information internally. Importantly, our scanning approach, without prior exposure to false statements, performs comparably to a fully supervised out-of-distribution classifier.","url_abs":"https://arxiv.org/abs/2312.02798v1","url_pdf":"https://arxiv.org/pdf/2312.02798v1.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":[{"paper_slug":"weakly-supervised-detection-of-hallucinations","repo_url":"https://github.com/Trusted-AI/adversarial-robustness-toolbox","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[{"method_slug":"opt","method_name":"OPT"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.02798","atlas_url":"https://app.syntology.ai/?focus=2312.02798","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02798"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Trusted-AI/adversarial-robustness-toolbox","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1},"by_repo_kind":{"official":{"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":"62ea3edf38aea545","entry":"shape_labels","repo":"Trusted-AI/adversarial-robustness-toolbox","repo_kind":"official","path":"art/attacks/poisoning/adversarial_embedding_attack.py","file_url":"https://github.com/Trusted-AI/adversarial-robustness-toolbox/blob/HEAD/art/attacks/poisoning/adversarial_embedding_attack.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"62ea3edf38aea545"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}