---
format: "aidr-story-markdown/v1"
id: "7f222ffac50d47c93f26b629cfc078e2bbb0afd40836e4d36cfdce6a3d1c218e"
canonical_url: "https://aidr.today/7f222ffa?lang=en"
title: "Check Token: Real-Time Self-Verification and Precise Truncation in LLM Reasoning"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-17T05:00:00.000Z"
category: "Research"
topics: ["reasoning"]
source_urls: ["https://arxiv.org/abs/2611.18564"]
summary: "ECC memory embeds 8 parity bits for every 64 data bits and automatically detects and corrects errors on each read. The parity bits carry no data and only safeguard integrity, at ~12.5% overhead. Yet the reasoning chains of large language models lack such built-in self-verification: once an error occurs it propagates along the chain, and existing methods can only verify externally after generation completes. We propose the check token, establishing built-in self-verification for language model generation streams for the first time: a functional marker is added to the vocabulary, and the model triggers self-checking (analysis, localization, truncation, rewriting) by outputting it at any position. The check token carries no reasoning content (discarded after triggering) and only safeguards reasoning correctness, directly corresponding to the role of ECC parity bits, also at only ~13% overhead. Speculative forking further eliminates false-positive latency, and segmented reward makes trigger timing end-to-end learnable."
---

# Check Token: Real\-Time Self\-Verification and Precise Truncation in LLM Reasoning

> [Open the canonical story](<https://aidr.today/7f222ffa?lang=en>)

**Published:** 2026-11-17T05:00:00.000Z
**Category:** Research
**Topics:** reasoning

## Summary

ECC memory embeds 8 parity bits for every 64 data bits and automatically detects and corrects errors on each read\. The parity bits carry no data and only safeguard integrity, at \~12\.5% overhead\. Yet the reasoning chains of large language models lack such built\-in self\-verification: once an error occurs it propagates along the chain, and existing methods can only verify externally after generation completes\. We propose the check token, establishing built\-in self\-verification for language model generation streams for the first time: a functional marker is added to the vocabulary, and the model triggers self\-checking \(analysis, localization, truncation, rewriting\) by outputting it at any position\. The check token carries no reasoning content \(discarded after triggering\) and only safeguards reasoning correctness, directly corresponding to the role of ECC parity bits, also at only \~13% overhead\. Speculative forking further eliminates false\-positive latency, and segmented reward makes trigger timing end\-to\-end learnable\.

## Sources

- [Story source](<https://arxiv.org/abs/2611.18564>)

