{"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/latent-causal-probing-a-formal-perspective-on","title":"Latent Causal Probing: A Formal Perspective on Probing with Causal Models of Data","arxiv_id":"2407.13765","date":"2024-07-18","proceeding":null,"authors":["Charles Jin","Martin Rinard"],"abstract":"As language models (LMs) deliver increasing performance on a range of NLP tasks, probing classifiers have become an indispensable technique in the effort to better understand their inner workings. A typical setup involves (1) defining an auxiliary task consisting of a dataset of text annotated with labels, then (2) supervising small classifiers to predict the labels from the representations of a pretrained LM as it processed the dataset. A high probing accuracy is interpreted as evidence that the LM has learned to perform the auxiliary task as an unsupervised byproduct of its original pretraining objective. Despite the widespread usage of probes, however, the robust design and analysis of probing experiments remains a challenge. We develop a formal perspective on probing using structural causal models (SCM). Specifically, given an SCM which explains the distribution of tokens observed during training, we frame the central hypothesis as whether the LM has learned to represent the latent variables of the SCM. Empirically, we extend a recent study of LMs in the context of a synthetic grid-world navigation task, where having an exact model of the underlying causal structure allows us to draw strong inferences from the result of probing experiments. Our techniques provide robust empirical evidence for the ability of LMs to induce the latent concepts underlying text.","url_abs":"https://arxiv.org/abs/2407.13765v2","url_pdf":"https://arxiv.org/pdf/2407.13765v2.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":"latent-causal-probing-a-formal-perspective-on","repo_url":"https://github.com/charlesjin/emergent-semantics","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"robust-design","task_name":"Robust Design"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.13765","atlas_url":"https://app.syntology.ai/?focus=2407.13765","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2407.13765"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2407.13765\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2407.13765"},"call":"get_concepts_for_paper(arxiv_id=\"2407.13765\")"}],"by_repo":[{"repo":"charlesjin/emergent-semantics","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2305.11169"],"harvested_for_calls":[{"arxiv_id":"2305.11169","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2305.11169"},"call":"get_harvested_code_for_paper(arxiv_id=\"2305.11169\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"c3b96a8655ce162305451974b01bddbd702d89c028842bc807a76a5d5431b9fa","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}