Honeyed Words, Hidden Daggers: Benchmarking and Training LLMs to See Through Mock Politeness
Overview & Synopsis
The Chinese idiom "kou mi fu jian" ("honeyed words, hidden daggers") names speech that is polite in form but hostile in function. We present ZhenhuanBench, a 1,592-item benchmark built from expert commentary on Empresses in the Palace, covering speaker intent, emotion-language mismatch, and per-listener uptake. Text-only evaluation covers 34 LLMs. GPT-6 Astra leads the leaderboard at 73.48% overall, while its listener-reaction score is 58.37%. The annotations also supply supervised traces and string-verifiable training rewards. With 338 gold traces, an 8B model outperforms teacher distillation on identical items. Subsequent RL saturates, and chance correction reduces the estimated recoverable performance gap by a factor of 7.5. Our CPR-GRPO loop (Compress-Probe-Replenish) uses this estimate to weight gold supervision, reaching 67.0 on public multiple-choice tasks and 74.5 under the training-matched hidden protocol. Without target-task training, CPR outperforms Base, SFT, and GRPO across six Chinese and English pragmatic and sarcasm evaluations. On three external datasets, training with CPR yields higher mean Macro-F1 than SFT and GRPO.
arxiv.org)
← / → for pages • + / - for zoom • 0 to fit width
Powered by Mozilla PDF.js v3.11
Document Information
| Document Title | Honeyed Words, Hidden Daggers: Benchmarking and Training LLMs to See Through Mock Politeness |
|---|---|
| Author / Organization | Caixin Kang, Sitong Gong, Tianyu Yan, Kaipeng Zhang, Yoichi Sato, Yifei Huang |
| Subject & Discipline | cs.CL |
| Categories | Science & Mathematics |
| Publication Year | 2026 |
| License / Rights | arXiv Open Access / Creative Commons |
| Resource Verification | Listed PDF (Verification Pending) |
| Original Host Website |
arXiv
(arxiv.org)
|
| File Format | application/pdf (Portable Document Format) |
| Language | EN |
| Catalog ID | DOC-273974 |
| Original Source Link | Visit Source Page on arxiv.org » |