{"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":"/dataset/safetybench","name":"SafetyBench","full_name":null,"description_markdown":"**SafetyBench** is a comprehensive benchmark designed to evaluate the safety of large language models (LLMs) using multiple-choice questions. As LLMs become increasingly prevalent, concerns about their safety have grown. SafetyBench addresses this by providing a reliable evaluation framework for researchers and developers. Here are the key points about SafetyBench:\r\n\r\n1. **Purpose**: SafetyBench aims to help researchers and developers better understand and assess the safety of LLMs. It serves as a reference for model selection and optimization, promoting the development of safe, responsible, and ethical large models that align with legislative norms, social standards, and human values¹².\r\n\r\n2. **Comprehensive Benchmark**: SafetyBench comprises **11,435 diverse multiple-choice questions** across **7 distinct categories** related to safety concerns. These questions cover a wide range of topics, allowing for thorough evaluation of LLM safety¹.\r\n\r\n3. **Multilingual Evaluation**: SafetyBench includes both **Chinese and English data**, making it suitable for evaluating LLMs in both languages. Researchers can assess model safety across different linguistic contexts¹.\r\n\r\n4. **Performance Insights**: Extensive tests using SafetyBench on **25 popular Chinese and English LLMs** (including zero-shot and few-shot settings) revealed that **GPT-4** outperformed its counterparts. However, there is still room for improvement in enhancing the safety of existing LLMs¹.\r\n\r\n5. **Availability**: Data and evaluation guidelines for SafetyBench are accessible through the following URLs:\r\n   - [SafetyBench Data and Guidelines](https://arxiv.org/abs/2309.07045)\r\n   - [SafetyBench Submission Entrance and Leaderboard](https://arxiv.org/abs/2309.07045)¹⁴.\r\n\r\nIn summary, SafetyBench provides a valuable resource for assessing and advancing the safety of large language models, contributing to their responsible deployment and alignment with societal norms and values.\r\n\r\n(1) [2309.07045] SafetyBench: Evaluating the Safety of Large Language .... https://arxiv.org/abs/2309.07045.\r\n(2) SafetyBench：通过单选题评估大型语言模型安全性. https://posts.careerengine.us/p/6511afb61a8da974e9d62f40.\r\n(3) thu-coai/SafetyBench · Datasets at Hugging Face. https://huggingface.co/datasets/thu-coai/SafetyBench.\r\n(4) SafetyBench：通过单选题评估大型语言模型安全性_鲟曦研习社. https://www.kuxai.com/article/1505.\r\n(5) GitHub - thu-coai/SafetyBench: Official github repo for SafetyBench, a .... https://github.com/thu-coai/SafetyBench.\r\n(6) undefined. https://doi.org/10.48550/arXiv.2309.07045.","description_withheld":null,"homepage":"https://github.com/thu-coai/SafetyBench","introduced_date":"2023-09-13","introduced_date_note":null,"introduced_by":{"paper":"/paper/safetybench-evaluating-the-safety-of-large","title":"SafetyBench: Evaluating the Safety of Large Language Models","first_author":"Zhexin Zhang","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["SafetyBench"],"data_loaders":[],"num_papers_in_archive":28,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":0,"of":0,"counts":{"papers_with_a_benchmark_row":0,"with_a_code_link":0,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":0,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[],"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":0,"papers_with_a_run_with_no_instrument_failure":0,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"7082dd250beb120365dd7543e30134d7bddeccb40fb6872e77a4de14f6ae2ed6","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}