{"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/pierce-the-mists-greet-the-sky-decipher","title":"Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis","arxiv_id":"2505.14406","date":"2025-05-20","proceeding":null,"authors":["Haoming Huang","Yibo Yan","Jiahao Huo","Xin Zou","Xinfeng Li","Kun Wang","Xuming Hu"],"abstract":"Large Language Models (LLMs), despite their remarkable capabilities, are hampered by hallucinations. A particularly challenging variant, knowledge overshadowing, occurs when one piece of activated knowledge inadvertently masks another relevant piece, leading to erroneous outputs even with high-quality training data. Current understanding of overshadowing is largely confined to inference-time observations, lacking deep insights into its origins and internal mechanisms during model training. Therefore, we introduce PhantomCircuit, a novel framework designed to comprehensively analyze and detect knowledge overshadowing. By innovatively employing knowledge circuit analysis, PhantomCircuit dissects the internal workings of attention heads, tracing how competing knowledge pathways contribute to the overshadowing phenomenon and its evolution throughout the training process. Extensive experiments demonstrate PhantomCircuit's effectiveness in identifying such instances, offering novel insights into this elusive hallucination and providing the research community with a new methodological lens for its potential mitigation.","url_abs":"https://arxiv.org/abs/2505.14406v2","url_pdf":"https://arxiv.org/pdf/2505.14406v2.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":[{"task_slug":"hallucination","task_name":"Hallucination"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.14406","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14406"}},"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/halfmorepiece/PhantomCircuit","reach":null}],"summary":{"ran_violates":1,"ran_draft_wrong":4,"ran":1,"ran_honours":1},"by_repo_kind":{"found_in_text":{"samples":7,"ran":7,"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":"011699c99d460851","entry":"_is_eos_token","repo":"halfmorepiece/PhantomCircuit","repo_kind":"found_in_text","path":"co_xsub_identifier.py","file_url":"https://github.com/halfmorepiece/PhantomCircuit/blob/HEAD/co_xsub_identifier.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"011699c99d460851"}},{"code_sha256_prefix":"942e288739fc5fad","entry":"clean_prompt_tokens","repo":"halfmorepiece/PhantomCircuit","repo_kind":"found_in_text","path":"co_xsub_identifier.py","file_url":"https://github.com/halfmorepiece/PhantomCircuit/blob/HEAD/co_xsub_identifier.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"942e288739fc5fad"}},{"code_sha256_prefix":"ff663579f9e9503f","entry":"compute_logprob_variance_across_masks","repo":"halfmorepiece/PhantomCircuit","repo_kind":"found_in_text","path":"co_xsub_identifier.py","file_url":"https://github.com/halfmorepiece/PhantomCircuit/blob/HEAD/co_xsub_identifier.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ff663579f9e9503f"}},{"code_sha256_prefix":"4e43ea55d6c051ca","entry":"get_top_k_predictions","repo":"halfmorepiece/PhantomCircuit","repo_kind":"found_in_text","path":"co_xsub_identifier.py","file_url":"https://github.com/halfmorepiece/PhantomCircuit/blob/HEAD/co_xsub_identifier.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4e43ea55d6c051ca"}},{"code_sha256_prefix":"de73d191312197fe","entry":"identify_xsub_by_phantomcircuit","repo":"halfmorepiece/PhantomCircuit","repo_kind":"found_in_text","path":"co_xsub_identifier.py","file_url":"https://github.com/halfmorepiece/PhantomCircuit/blob/HEAD/co_xsub_identifier.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"de73d191312197fe"}},{"code_sha256_prefix":"ce9db70729fd9a34","entry":"safe_to_str_tokens","repo":"halfmorepiece/PhantomCircuit","repo_kind":"found_in_text","path":"co_xsub_identifier.py","file_url":"https://github.com/halfmorepiece/PhantomCircuit/blob/HEAD/co_xsub_identifier.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ce9db70729fd9a34"}},{"code_sha256_prefix":"7967a02919473231","entry":"safe_to_tokens","repo":"halfmorepiece/PhantomCircuit","repo_kind":"found_in_text","path":"co_xsub_identifier.py","file_url":"https://github.com/halfmorepiece/PhantomCircuit/blob/HEAD/co_xsub_identifier.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7967a02919473231"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}