In the news
Artificial Epanorthosis: Why large language models overuse a classical rhetorical figure, and how to mitigate it
arXiv cs.AI · Published · 3 min read
In 30 seconds
- What happened
- LLMs systematically overuse epanorthosis, a classical self-correction rhetorical figure, driven by training data and preference tuning rather than generation mechanics.
- Why it matters
- Matters for engineers building or fine-tuning language models who want output matching human rhetorical patterns across different writing genres and registers.
- Watch out
- The paper measures only one model family; mitigation techniques like LoRA adapters and instruction tuning show promise but require genre-specific calibration rather than outright elimination.
- language model
The patterns behind this
- Privilege Compromise Mitigation Pattern
- Agentic Context Engineering (Evolving Playbook)
- Reinforcement Learning from Human Feedback
Each one covers how the technique works, when it earns its cost, and where it breaks.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.