{"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/looking-inward-language-models-can-learn","title":"Looking Inward: Language Models Can Learn About Themselves by Introspection","arxiv_id":"2410.13787","date":"2024-10-17","proceeding":null,"authors":["Felix J Binder","James Chua","Tomek Korbak","Henry Sleight","John Hughes","Robert Long","Ethan Perez","Miles Turpin","Owain Evans"],"abstract":"Humans acquire knowledge by observing the external world, but also by introspection. Introspection gives a person privileged access to their current state of mind (e.g., thoughts and feelings) that is not accessible to external observers. Can LLMs introspect? We define introspection as acquiring knowledge that is not contained in or derived from training data but instead originates from internal states. Such a capability could enhance model interpretability. Instead of painstakingly analyzing a model's internal workings, we could simply ask the model about its beliefs, world models, and goals. More speculatively, an introspective model might self-report on whether it possesses certain internal states such as subjective feelings or desires and this could inform us about the moral status of these states. Such self-reports would not be entirely dictated by the model's training data. We study introspection by finetuning LLMs to predict properties of their own behavior in hypothetical scenarios. For example, \"Given the input P, would your output favor the short- or long-term option?\" If a model M1 can introspect, it should outperform a different model M2 in predicting M1's behavior even if M2 is trained on M1's ground-truth behavior. The idea is that M1 has privileged access to its own behavioral tendencies, and this enables it to predict itself better than M2 (even if M2 is generally stronger). In experiments with GPT-4, GPT-4o, and Llama-3 models (each finetuned to predict itself), we find that the model M1 outperforms M2 in predicting itself, providing evidence for introspection. Notably, M1 continues to predict its behavior accurately even after we intentionally modify its ground-truth behavior. However, while we successfully elicit introspection on simple tasks, we are unsuccessful on more complex tasks or those requiring out-of-distribution generalization.","url_abs":"https://arxiv.org/abs/2410.13787v1","url_pdf":"https://arxiv.org/pdf/2410.13787v1.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":"looking-inward-language-models-can-learn","repo_url":"https://github.com/felixbinder/introspection_self_prediction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"out-of-distribution-generalization","task_name":"Out-of-Distribution Generalization"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.13787","atlas_url":"https://app.syntology.ai/?focus=2410.13787","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13787"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.13787"},"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":"2410.13787"},"call":"get_harvested_code_for_paper(arxiv_id=\"2410.13787\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2410.13787"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2410.13787\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2410.13787"},"call":"get_concepts_for_paper(arxiv_id=\"2410.13787\")"}],"by_repo":[{"repo":"felixbinder/introspection_self_prediction","kind":"official","samples":4,"ran":3,"instrument":1,"unverified":1}],"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/2410.13787.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/2410.13787.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/felixbinder/introspection_self_prediction","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran":2,"unverified":1},"n_samples":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"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":4,"ran":3,"n_ran_checked":2,"n_instrument":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":4,"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":3,"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"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"a2e49f02b84ed98b","code_sha256_prefix":"a2e49f02b84ed98b","entry":"deterministic_hash","repo":"felixbinder/introspection_self_prediction","repo_kind":"official","path":"evals/data_models/hashable.py","file_url":"https://github.com/felixbinder/introspection_self_prediction/blob/HEAD/evals/data_models/hashable.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":"something: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":"a2e49f02b84ed98b"},"code_page":"/code/deterministic-hash","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, felixbinder/introspection_self_prediction when it was checked","mcp_get_code":{"code_sha256":"a2e49f02b84ed98b"}},{"code_sha256":"b1dd710056d0299f","code_sha256_prefix":"b1dd710056d0299f","entry":"extract_strings","repo":"felixbinder/introspection_self_prediction","repo_kind":"official","path":"evals/extract_strings_from_dataframe.py","file_url":"https://github.com/felixbinder/introspection_self_prediction/blob/HEAD/evals/extract_strings_from_dataframe.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"input_file_paths:list/1/PosixPath, n_out_strings:float/0/float, output_file_path:PosixPath/0/?, seed:int/0/int","fixture_out_type":"PosixPath","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, felixbinder/introspection_self_prediction when it was checked","mcp_get_code":{"code_sha256":"b1dd710056d0299f"}},{"code_sha256":"43066566684c556a","code_sha256_prefix":"43066566684c556a","entry":"train_val_split","repo":"felixbinder/introspection_self_prediction","repo_kind":"official","path":"evals/extract_strings_from_dataframe.py","file_url":"https://github.com/felixbinder/introspection_self_prediction/blob/HEAD/evals/extract_strings_from_dataframe.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"full_string_path:PosixPath/0/?, split:float/0/float, seed:int/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/train-val-split","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, felixbinder/introspection_self_prediction when it was checked","mcp_get_code":{"code_sha256":"43066566684c556a"}},{"code_sha256":"4b566b1da0fc850f","code_sha256_prefix":"4b566b1da0fc850f","entry":"load_hydra_config","repo":"felixbinder/introspection_self_prediction","repo_kind":"official","path":"evals/create_finetuning_dataset.py","file_url":"https://github.com/felixbinder/introspection_self_prediction/blob/HEAD/evals/create_finetuning_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, felixbinder/introspection_self_prediction when it was checked","mcp_get_code":{"code_sha256":"4b566b1da0fc850f"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"db9bff39fde63eaec6b38e8cc6a8301acf564d3c5ca3d588e22add126e4dc890","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}