arXiv (OAI Expanded)
open access
Off-Target Effects of Response-Style Alignment in a Korean 27B Language Model
We post-train Qwen3.8-27B for Korean response style -- verbosity, list and markdown usage, discourse structure and register -- and measure two behaviours the objective never targets: abstention on ambiguous social questions in KoBBQ, where the benchmark-correct answer is UNKNOWN, and unprompted disc
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
- The processing of multi-word expressions in L1 and L2 Chinese: Evidence from reaction times and eye movements#344093
- Large language models infer hidden preferences from eye movements but fail to exploit response times#372306
- Language models suffer from a curse of ambiguity#616614
- Language models suffer from a curse of ambiguity#616114
- Is Prosody Lost in Translation? Fine-Grained Cross-Lingual Prosody Similarity Across Languages#781134
Record · ID 1110355
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