{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/unveiling-llms-the-evolution-of-latent","title":"Unveiling LLMs: The Evolution of Latent Representations in a Dynamic Knowledge Graph","arxiv_id":"2404.03623","date":"2024-04-04","proceeding":null,"authors":["Marco Bronzini","Carlo Nicolini","Bruno Lepri","Jacopo Staiano","Andrea Passerini"],"abstract":"Large Language Models (LLMs) demonstrate an impressive capacity to recall a vast range of factual knowledge. However, understanding their underlying reasoning and internal mechanisms in exploiting this knowledge remains a key research area. This work unveils the factual information an LLM represents internally for sentence-level claim verification. We propose an end-to-end framework to decode factual knowledge embedded in token representations from a vector space to a set of ground predicates, showing its layer-wise evolution using a dynamic knowledge graph. Our framework employs activation patching, a vector-level technique that alters a token representation during inference, to extract encoded knowledge. Accordingly, we neither rely on training nor external models. Using factual and common-sense claims from two claim verification datasets, we showcase interpretability analyses at local and global levels. The local analysis highlights entity centrality in LLM reasoning, from claim-related information and multi-hop reasoning to representation errors causing erroneous evaluation. On the other hand, the global reveals trends in the underlying evolution, such as word-based knowledge evolving into claim-related facts. By interpreting semantics from LLM latent representations and enabling graph-related analyses, this work enhances the understanding of the factual knowledge resolution process.","url_abs":"https://arxiv.org/abs/2404.03623v2","url_pdf":"https://arxiv.org/pdf/2404.03623v2.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":"unveiling-llms-the-evolution-of-latent","repo_url":"https://github.com/Ipazia-AI/latent-explorer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"claim-verification","task_name":"Claim Verification"},{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"knowledge-probing","task_name":"Knowledge Probing"},{"task_slug":"probing-language-models","task_name":"Probing Language Models"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"patching","method_name":"Patching"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.03623","atlas_url":"https://app.syntology.ai/?focus=2404.03623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03623"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2404.03623"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2404.03623"},"call":"get_harvested_code_for_paper(arxiv_id=\"2404.03623\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2404.03623"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2404.03623\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2404.03623"},"call":"get_concepts_for_paper(arxiv_id=\"2404.03623\")"}],"by_repo":[{"repo":"Ipazia-AI/latent-explorer","kind":"official","samples":5,"ran":5,"instrument":2,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2404.03623.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2404.03623.svg"},"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/Ipazia-AI/latent-explorer","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_draft_wrong":2,"ran":3},"n_samples":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":5,"ran":5,"n_ran_checked":3,"n_instrument":2,"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,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":5,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"samples":[{"code_sha256":"16d2e995ac19cde3","code_sha256_prefix":"16d2e995ac19cde3","entry":"clean_token","repo":"Ipazia-AI/latent-explorer","repo_kind":"official","path":"src/latent_explorer/utils/utils.py","file_url":"https://github.com/Ipazia-AI/latent-explorer/blob/HEAD/src/latent_explorer/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"token:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"16d2e995ac19cde3"},"code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, Ipazia-AI/latent-explorer (NOASSERTION)","mcp_get_code":{"code_sha256":"16d2e995ac19cde3"}},{"code_sha256":"ff33322f639624be","code_sha256_prefix":"ff33322f639624be","entry":"clearString","repo":"Ipazia-AI/latent-explorer","repo_kind":"official","path":"src/latent_explorer/utils/graph.py","file_url":"https://github.com/Ipazia-AI/latent-explorer/blob/HEAD/src/latent_explorer/utils/graph.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"s:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"ff33322f639624be"},"code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, Ipazia-AI/latent-explorer (NOASSERTION)","mcp_get_code":{"code_sha256":"ff33322f639624be"}},{"code_sha256":"3cdb089cb92bdcb7","code_sha256_prefix":"3cdb089cb92bdcb7","entry":"draw_temporal_graph","repo":"Ipazia-AI/latent-explorer","repo_kind":"official","path":"src/latent_explorer/utils/graph.py","file_url":"https://github.com/Ipazia-AI/latent-explorer/blob/HEAD/src/latent_explorer/utils/graph.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"TG:list/1/DiGraph, suptitle:str/0/str","fixture_out_type":"Figure","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, Ipazia-AI/latent-explorer (NOASSERTION)","mcp_get_code":{"code_sha256":"3cdb089cb92bdcb7"}},{"code_sha256":"1ee898f665a042a8","code_sha256_prefix":"1ee898f665a042a8","entry":"generateSPOTriples","repo":"Ipazia-AI/latent-explorer","repo_kind":"official","path":"src/latent_explorer/utils/triples.py","file_url":"https://github.com/Ipazia-AI/latent-explorer/blob/HEAD/src/latent_explorer/utils/triples.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"items:list/1/str, verbose:bool/0/bool","fixture_out_type":"list","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, Ipazia-AI/latent-explorer (NOASSERTION)","mcp_get_code":{"code_sha256":"1ee898f665a042a8"}},{"code_sha256":"3a679a4906fb070b","code_sha256_prefix":"3a679a4906fb070b","entry":"generate_prompt_template","repo":"Ipazia-AI/latent-explorer","repo_kind":"official","path":"src/latent_explorer/utils/utils.py","file_url":"https://github.com/Ipazia-AI/latent-explorer/blob/HEAD/src/latent_explorer/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"sys_prompt:str/0/str, examples:list/1/dict, input_text:str/0/str, role_sys_available:bool/0/bool","fixture_out_type":"list","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, Ipazia-AI/latent-explorer (NOASSERTION)","mcp_get_code":{"code_sha256":"3a679a4906fb070b"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"8d7f403f90bc6bc3ea53d58d96f2d72be728a282e13bc1fab0259dae044ee848","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}