ziansu/awesome-llm-steering

A collection of papers related to steering of (multimodal) large language models.

22
/ 100
Experimental

This collection helps researchers and practitioners explore methods to precisely control the behavior and outputs of large language models (LLMs) and multimodal LLMs. It compiles academic papers, blogs, and tools that demonstrate how to influence what an AI model generates without needing to retrain it. The audience for this resource is AI researchers and ML engineers focusing on model interpretability, safety, and fine-grained control.

No commits in the last 6 months.

Use this if you are an AI researcher or ML engineer looking for advanced techniques to understand, modify, or steer the internal workings and outputs of large language models.

Not ideal if you are a non-technical user simply looking for better ways to prompt an LLM or use an off-the-shelf AI application.

AI research ML engineering LLM interpretability Model control AI safety
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 15 / 25
Community 0 / 25

How are scores calculated?

Stars

9

Forks

Language

License

Apache-2.0

Last pushed

Sep 30, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/ziansu/awesome-llm-steering"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.