arXiv (All)
open access
Style, Not Self: Surface Cues Explain Zero-Shot Code Attribution by Large Language Models
If a language model can recognize code it wrote, it may favor that code as a judge, and instances of one model monitoring each other could collude. We test this zero-shot on current commercial models. Five LLMs generate solutions to MBPP, HumanEval, and DS-1000, seven more to MBPP, and models act as
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
- From Role Prompt to Infinite Thinking: Exploiting Persona Conditioning for Inference Cost Attacks in LLMs#410959
- Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm#16626
- Understanding the (In)Security of Vibe-Coded Applications#1110278
- Logits are All We Need to Adapt Closed Models#1036540
- Watermarkable Multi-Draft Speculative Sampling via Poisson Processes#1036247
Record · ID 1078119
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