arXiv (All)
open access
GlitchPatch: Repairing Glitch Tokens in Frozen Language Models via Local Retokenization
Glitch tokens are anomalous vocabulary entries that can cause large language models (LLMs) to produce outputs inconsistent with their inputs. Existing repair methods require access to model internals, making them impractical for frozen checkpoints. We investigate whether glitch tokens can be repaire
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Adversarial Reframing: A Framework for Targeted Generation in Language Models#216742
- Quantifying and Mitigating Korean Jamo-Level Typographical Vulnerabilities in Large Language Models#799449
- Quantifying and Mitigating Korean Jamo-Level Typographical Vulnerabilities in Large Language Models#798026
- In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning#987009
- Commit Locally, Exit Globally: Coordinating Adaptive Sampling and Early Exit in Diffusion Language Models#1344663
Record · ID 1200050
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive