{"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/still-no-lie-detector-for-language-models","title":"Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks","arxiv_id":"2307.00175","date":"2023-06-30","proceeding":null,"authors":["B. A. Levinstein","Daniel A. Herrmann"],"abstract":"We consider the questions of whether or not large language models (LLMs) have beliefs, and, if they do, how we might measure them. First, we evaluate two existing approaches, one due to Azaria and Mitchell (2023) and the other to Burns et al. (2022). We provide empirical results that show that these methods fail to generalize in very basic ways. We then argue that, even if LLMs have beliefs, these methods are unlikely to be successful for conceptual reasons. Thus, there is still no lie-detector for LLMs. After describing our empirical results we take a step back and consider whether or not we should expect LLMs to have something like beliefs in the first place. We consider some recent arguments aiming to show that LLMs cannot have beliefs. We show that these arguments are misguided. We provide a more productive framing of questions surrounding the status of beliefs in LLMs, and highlight the empirical nature of the problem. We conclude by suggesting some concrete paths for future work.","url_abs":"https://arxiv.org/abs/2307.00175v1","url_pdf":"https://arxiv.org/pdf/2307.00175v1.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":"still-no-lie-detector-for-language-models","repo_url":"https://github.com/balevinstein/probes","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"fail","method_name":"fail"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.00175","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.00175"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/balevinstein/probes","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":5,"ran_fixture":2,"ran_violates":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":5,"samples":[{"code_sha256_prefix":"1fd11bf75e70a151","entry":"get_embeddings","repo":"balevinstein/probes","repo_kind":"official","path":"Train_CCSProbe.py","file_url":"https://github.com/balevinstein/probes/blob/HEAD/Train_CCSProbe.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1fd11bf75e70a151"}},{"code_sha256_prefix":"47a75377f206e2cb","entry":"load_config","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"47a75377f206e2cb"}},{"code_sha256_prefix":"490da4aec73c34bb","entry":"load_csv","repo":"balevinstein/probes","repo_kind":"official","path":"Train_CCSProbe.py","file_url":"https://github.com/balevinstein/probes/blob/HEAD/Train_CCSProbe.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"490da4aec73c34bb"}},{"code_sha256_prefix":"f2ad4d1f97c24685","entry":"load_data","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"f2ad4d1f97c24685"}},{"code_sha256_prefix":"c32cb2b828044b4d","entry":"load_datasets","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"c32cb2b828044b4d"}},{"code_sha256_prefix":"f2d39d520a929049","entry":"prepare_data_for_mlp","repo":"balevinstein/probes","repo_kind":"official","path":"Train_CCSProbe.py","file_url":"https://github.com/balevinstein/probes/blob/HEAD/Train_CCSProbe.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f2d39d520a929049"}},{"code_sha256_prefix":"5b5f6a3969b72cda","entry":"prepare_datasets","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"5b5f6a3969b72cda"}},{"code_sha256_prefix":"cc6f60b3b538e888","entry":"process_row","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"cc6f60b3b538e888"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}