LLMs Corrupt Your Documents When You Delegate
A recent study reveals that Large Language Models (LLMs) can significantly degrade document quality during delegated tasks. The research, conducted using a new framework called DELEGATE-52, found that even advanced models corrupt an average of 25% of document content. This raises concerns about the reliability of LLMs in professional workflows, as errors can accumulate over time.
- ▪The study introduced DELEGATE-52 to evaluate LLM performance in delegated workflows across 52 professional domains.
- ▪Current LLMs, including Gemini 3.1 Pro and GPT 5.4, were found to corrupt an average of 25% of document content during long interactions.
- ▪The degradation of documents was exacerbated by factors such as document size and the presence of distractor files.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv.org |
| Canonical URL | https://arxiv.org/abs/2604.15597 |
| Publication time | Tue, 28 Apr 2026 12:49:38 +0000 |
| Retrieval time | 2026-04-28T12:54:31.957Z |
| Last seen | 2026-04-28T12:54:31.957Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | wiGAj_6-7FYX |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Computation and Language arXiv:2604.15597 (cs) [Submitted on 17 Apr 2026] Title:LLMs Corrupt Your Documents When You Delegate Authors:Philippe Laban, Tobias Schnabel, Jennifer Neville View a PDF of the paper titled LLMs Corrupt Your Documents When You Delegate, by Philippe Laban and Tobias Schnabel and Jennifer Neville View PDF HTML (experimental) Abstract: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.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv.org.
Discussion
0 commentsMore from arXiv.org
