Delegated Editing & Document Corruption
The risk that surfaces when a user hands off document-editing tasks to an LLM expecting faithful execution — unintended, often silent degradation of content introduced during the edit.
Also known as: delegation, document corruption
Part of: LLM Limitations
How authors use it
Oldest first (extraction date when no publication date is known).
| Author | Their term | Their meaning |
|---|---|---|
| LLMs Corrupt Your Documents When You Delegate Philippe Laban, Tobias Schnabel, Jennifer Neville · 2026-04-17 | delegation | An interaction paradigm where users hand off document-editing tasks to an LLM with the expectation of faithful execution — distinct from conversational or co-editing use |
| LLMs Corrupt Your Documents When You Delegate Philippe Laban, Tobias Schnabel, Jennifer Neville · 2026-04-17 | document corruption | Unintended degradation of document content introduced by the LLM during editing, measured as percentage of content corrupted |
| Portal by Spotify cut my Claude Code token usage by 90% Dimitri Mazmanov · 2026-09-03 | Delegation | Routing an entire sub-task's execution (reading a set of files and answering about them; generating a file from a spec and reference) to the worker model such that the corpus or generated code never enters Claude's own context — Claude sees only the compact result. |
Documents (2)
- Portal by Spotify cut my Claude Code token usage by 90% Dimitri Mazmanov · 2026-09-03 source ↗ Reader 🖥️
Because most of what a coding agent does is I/O rather than reasoning, routing that I/O-bound work (bulk file reads, pattern-following boilerplate generation) to a cheap worker model — and enforcing that routing deterministically via harness-level hooks rather than relying on advisory instructions the model can ignore — cuts Claude Code's token spend by around 90% on the delegated work while reserving the frontier model for editing, debugging, and anything safety-critical. - LLMs Corrupt Your Documents When You Delegate Philippe Laban, Tobias Schnabel, Jennifer Neville · 2026-04-17 source ↗ Reader 🖥️
Current LLMs are unreliable delegates that silently corrupt documents during long delegated workflows, as demonstrated by the DELEGATE-52 benchmark across 52 professional domains and 19 models.
Propositions touching this concept (4)
By publication month, oldest first (extraction month when no publication date is known).
2026-04
- explicitDelegation is emerging as a new interaction paradigm for LLMs in knowledge work.
- explicitDelegation requires trust that the LLM will faithfully execute tasks without introducing errors.
2026-09
- explicitPreToolUse hooks that deterministically block Read calls above a configurable line threshold (default 350) and equivalent bash reads (cat/head/tail/less/more on large files) enforce delegation to the bulk-reader mode regardless of whether Claude reads or follows written routing instructions.
- explicitEach delegation is a network round trip (Claude Code to the Portal backend to the worker model and back) typically taking 10-30 seconds, with Portal capping a single invocation at 30 seconds, making delegation counterproductive for reads below the configured line threshold.
Open gaps (4)
- incompleteThe abstract does not define what counts as 'corruption' — whether it includes formatting changes, semantic drift, factual errors, or data loss. The 25% figure is hard to evaluate without knowing the corruption metric.LLMs Corrupt Your Documents When You Delegate — read next: Read the full paper's methodology section to understand how corruption is operationalized and measured.
- incompleteThe abstract does not clarify what 'agentic tool use' configurations were tested. The negative result (tools don't help) is only as strong as the range of agentic approaches evaluated.LLMs Corrupt Your Documents When You Delegate — read next: Read the full paper's experimental setup for agentic configurations.
- incompleteNo discussion of whether corruption rates vary significantly across the 52 domains. Some domains (e.g., music notation, crystallography) may have much stricter fidelity requirements than others.LLMs Corrupt Your Documents When You Delegate — read next: Check the full paper for per-domain breakdowns.
- incompleteExtraction limited to abstract only (242 words). The full paper likely contains detailed methodology, per-model results, domain breakdowns, and qualitative error analysis not available here.LLMs Corrupt Your Documents When You Delegate — read next: Obtain and extract the full PDF at https://arxiv.org/pdf/2604.15597