Termsslug: activation-steering

Activation Steering

激活引导

Technique controlling model output by modifying internal activation values

Curated Intelligence

2 items · Page 1/1
Hacker News AIT2·Models
68 pts
Qwen3-4B Fine-tuned to Remove AI Writing Tics

A developer released a fine-tuned Qwen3-4B model that significantly reduces 'AI writing tics' like excessive clause chaining and vague positioning through multi-round distillation and rule-based checks. The model maintains task adherence while minimizing hallucinated citations and syntactic redundancy.

Apple Machine Learning ResearchT1·Models
68 pts
Study Reveals Trade-Offs in LLM Conditioning Methods

A new systematic study reveals that efficient activation steering methods for LLM conditioning often compromise generation fluency. It highlights a critical interaction where instruction tuning significantly reduces the effectiveness of steering compared to base models, while prompting and SFT are better at concept injection than removal. Additionally, cheap textual metrics were found to highly correlate with costly LLM-as-judge scores.