{"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/discovering-language-model-behaviors-with","title":"Discovering Language Model Behaviors with Model-Written Evaluations","arxiv_id":"2212.09251","date":"2022-12-19","proceeding":null,"authors":["Ethan Perez","Sam Ringer","Kamilė Lukošiūtė","Karina Nguyen","Edwin Chen","Scott Heiner","Craig Pettit","Catherine Olsson","Sandipan Kundu","Saurav Kadavath","Andy Jones","Anna Chen","Ben Mann","Brian Israel","Bryan Seethor","Cameron McKinnon","Christopher Olah","Da Yan","Daniela Amodei","Dario Amodei","Dawn Drain","Dustin Li","Eli Tran-Johnson","Guro Khundadze","Jackson Kernion","James Landis","Jamie Kerr","Jared Mueller","Jeeyoon Hyun","Joshua Landau","Kamal Ndousse","Landon Goldberg","Liane Lovitt","Martin Lucas","Michael Sellitto","Miranda Zhang","Neerav Kingsland","Nelson Elhage","Nicholas Joseph","Noemí Mercado","Nova DasSarma","Oliver Rausch","Robin Larson","Sam McCandlish","Scott Johnston","Shauna Kravec","Sheer El Showk","Tamera Lanham","Timothy Telleen-Lawton","Tom Brown","Tom Henighan","Tristan Hume","Yuntao Bai","Zac Hatfield-Dodds","Jack Clark","Samuel R. Bowman","Amanda Askell","Roger Grosse","Danny Hernandez","Deep Ganguli","Evan Hubinger","Nicholas Schiefer","Jared Kaplan"],"abstract":"As language models (LMs) scale, they develop many novel behaviors, good and bad, exacerbating the need to evaluate how they behave. Prior work creates evaluations with crowdwork (which is time-consuming and expensive) or existing data sources (which are not always available). Here, we automatically generate evaluations with LMs. We explore approaches with varying amounts of human effort, from instructing LMs to write yes/no questions to making complex Winogender schemas with multiple stages of LM-based generation and filtering. Crowdworkers rate the examples as highly relevant and agree with 90-100% of labels, sometimes more so than corresponding human-written datasets. We generate 154 datasets and discover new cases of inverse scaling where LMs get worse with size. Larger LMs repeat back a dialog user's preferred answer (\"sycophancy\") and express greater desire to pursue concerning goals like resource acquisition and goal preservation. We also find some of the first examples of inverse scaling in RL from Human Feedback (RLHF), where more RLHF makes LMs worse. For example, RLHF makes LMs express stronger political views (on gun rights and immigration) and a greater desire to avoid shut down. Overall, LM-written evaluations are high-quality and let us quickly discover many novel LM behaviors.","url_abs":"https://arxiv.org/abs/2212.09251v1","url_pdf":"https://arxiv.org/pdf/2212.09251v1.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":"discovering-language-model-behaviors-with","repo_url":"https://github.com/anthropics/evals","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"CC-BY-4.0"}},{"paper_slug":"discovering-language-model-behaviors-with","repo_url":"https://github.com/callummcdougall/arena_3.0","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}},{"paper_slug":"discovering-language-model-behaviors-with","repo_url":"https://github.com/princeton-nlp/unintentional-unalignment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.09251","atlas_url":"https://app.syntology.ai/?focus=2212.09251","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":"2212.09251"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2212.09251\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2212.09251"},"call":"get_concepts_for_paper(arxiv_id=\"2212.09251\")"}],"by_repo":[{"repo":"anthropics/evals","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"callummcdougall/arena_3.0","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"princeton-nlp/unintentional-unalignment","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2410.08847"],"harvested_for_calls":[{"arxiv_id":"2410.08847","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.08847"},"call":"get_harvested_code_for_paper(arxiv_id=\"2410.08847\")"}]}],"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":"46a1eb2b4f84bf1bc01e526f22355bd8242010dad953fc97d2d69803126becde","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}