LLMs Corrupt Your Documents When You DelegatePhilippe Laban, Tobias Schnabel, Jennifer Neville (#Microsoft Research)Larg...

LLMs Corrupt Your Documents When You DelegatePhilippe Laban, Tobias Schnabel, Jennifer Neville (#Microsoft Research)Large Language Models (#LLMs) are poised to disrupt knowledge work, with the emergence of delegated work as a new interaction paradigm (e.g., vibe coding). Delegation requires trust - the expectation that the LLM will faithfully execute the task without introducing errors into documents. We introduce DELEGATE-52 to study the readiness of AI systems in delegated workflows. DELEGATE-52 simulates long delegated workflows that require in-depth document editing across 52 professional domains, such as coding, crystallography, and music notation. Our large-scale experiment with 19 LLMs reveals that current models degrade documents during delegation: even frontier models (#Gemini 3.1 Pro, #Claude 4.6 Opus, #GPT 5.4) #corrupt an average of 25% of document content by the end of long workflows, with other models failing more severely. https://doi.org/10.48550/arXiv.2604.15597#agenti...

Read Original

Related

Mastodon discussion 40m ago

シグルドさんはReshiについても詳しいですiPhone Duoがミニノートに? iPhone Duo上で脱獄せずにWindows 11を動かす動画が公開中【やじうまWatch】 https://internet.watch.impress...

シグルドさんはReshiについても詳しいですiPhone Duoがミニノートに? iPhone Duo上で脱獄せずにWindows 11を動かす動画が公開中【やじうまWatch】 https://internet.watch.impress.co.jp/docs/yajiuma/2157751.html#Apple #LLM #news #bot