Steering Language Models With Activation Engineering — mentioned by smokel

Mon, 12 May 2025 18:09:46 GMT

Not an expert in the field, but apparently there has been some research into this. It's called inference-time intervention [1], [2]. [1] "Steering Language Models With Activation Engineering", 2023, https://arxiv.org/abs/2308.10248 [2] "Multi-Attribute Steering of Language Models via Targeted Intervention", 2025, https://arxiv.org/pdf/2502.12446

Paper and discussion history. A mention is not an endorsement.

Steering Language Models With Activation Engineering — mentioned by emrek1

Tue, 12 Mar 2024 01:20:05 GMT

Each of those is great, and more sophisticated strategies are being developed all the time: incorporating static analysis at inference time to ensure code is more than just syntactically correct [0]; to multi-LLM call agent-based frameworks [1]; decomposing hard tasks into many "easier" LLM tasks [2]; analyzing internal activations to identify potential hallucinations [3]; activation steering to control generations [4]; and "Language Model Arithmetic" to compose biases for style, vocab, etc [5]. But each also either requires tight integration with an LLM inference/serving engine (to access…

Paper and discussion history. A mention is not an endorsement.

Steering Language Models With Activation Engineering · HackerPapers discussions

Steering Language Models With Activation Engineering — mentioned by smokel

Steering Language Models With Activation Engineering — mentioned by emrek1