{"type":"post","id":"benchmirt-disentangling-safety-and-general-capabilities-in-llm-7d74ef","slug":"benchmirt-disentangling-safety-and-general-capabilities-in-llm-7d74ef","title":"BenchMIRT: Disentangling Safety and General Capabilities in LLM Evaluation","description":"Allen Institute for AI and Carnegie Mellon University researchers introduced BenchMIRT, a two-dimensional multidimensional Item Response Theory method for auditing what LLM safety and reasoning benchmarks measure.","retrieval_nugget":"Allen Institute for AI and Carnegie Mellon University researchers introduced BenchMIRT, a two-dimensional multidimensional Item Response Theory method for auditing what LLM safety and reasoning benchmarks measure.","published_at":"2026-10-23","updated_at":"2026-10-23","record_date":"2026-10-23","date_kind":"published_at","topics":["evals","ai-security"],"entities":["BenchMIRT","Allen Institute for AI","Carnegie Mellon University","Multidimensional Item Response Theory","BBQ","WMDP","XSTest","WildJailbreak"],"related_patterns":["ai-engineering-evaluations-are-splitting-into-task-specific"],"novelty_label":"same_event","what_changed":"Same event as BenchMIRT: What are LLM benchmarks actually measuring?","prior_refs":["memory:6c62c2e8-e513-8727-acd1-572cad479e33"],"source_url":"https://allenai.org/papers/benchmirt","source_urls":["https://allenai.org/papers/benchmirt"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:benchmirt-disentangling-safety-and-general-capabilities-in-llm-7d74ef","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/benchmirt-disentangling-safety-and-general-capabilities-in-llm-7d74ef/","markdown":"https://newruntime.com/posts/benchmirt-disentangling-safety-and-general-capabilities-in-llm-7d74ef.md","json":"https://newruntime.com/posts/benchmirt-disentangling-safety-and-general-capabilities-in-llm-7d74ef.json"},"next_reads":[{"type":"topic","path":"/topics/evals/","url":"https://newruntime.com/topics/evals/","title":"Evals","reason":"Explore the evals topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/evals.md","json_url":"https://newruntime.com/topics/evals.json"},{"type":"topic","path":"/topics/ai-security/","url":"https://newruntime.com/topics/ai-security/","title":"Ai Security","reason":"Explore the ai-security topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/ai-security.md","json_url":"https://newruntime.com/topics/ai-security.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}