Rhetorical Questions in LLM Representations: A Linear Probing Study
Quick summary
arXiv:2604.14128v3 Announce Type: replace-cross Abstract: Rhetorical questions are asked not to seek information but to persuade or signal stance. How large language models internally represent them remains unclear. We analyze rhetorical questions in LLM representations using linear probes on two social-media datasets with different discourse contexts, and find that rhetorical signals emerge early and are most stably captured by last-token representations. Rhetorical questions are linearly separable from information-seeking questions within datasets, and remain detectable under cross-dataset t
Key takeaways
- arXiv:2604.14128v3 Announce Type: replace-cross Abstract: Rhetorical questions are asked not to seek information but to persuade or signal stance.
- How large language models internally represent them remains unclear.
- We analyze rhetorical questions in LLM representations using linear probes on two social-media datasets with different discourse contexts, and find that rhetorical signals emerge early and are most stably captured by last-token representations.
Why it matters
“Rhetorical Questions in LLM Representations: A Linear Probing Study” highlights the need for repeatable measurement rather than a single impressive demonstration. Independent validation across datasets and clearly stated limitations determine whether a result can guide product decisions.
Member comments