paper-with-me

Papers

Steering Large Language Models with Feature Guided Activation Additions

2025-01-17 · Samuel Soo, Wesley Teng, Chandrasekaran Balaganesh

Effective and reliable control over large language model (LLM) behavior is a significant challenge. While activation steering methods, which add steering vectors to a model's hidden states, are a promising approach, existing techniques often lack precision and interpretability in how they influence model outputs. We introduce Feature Guided Activation Additions (FGAA), a novel activation steering method that leverages insights from Contrastive Activation Addition (CAA) and Sparse Autoencoder-Targeted Steering (SAE-TS). By operating in the latent space of a Sparse Autoencoder (SAE) and employing optimization techniques to select desired SAE features, FGAA constructs precise steering vectors that provide better steering effects while maintaining coherence of steered model outputs. In this regard, evaluations on Gemma-2-2B and Gemma-2-9B models across various steering tasks demonstrate that FGAA outperforms existing steering methods of CAA, SAE decoder steering, and SAE-TS. Our results also highlight important trade-offs between steering scale and general model capabilities that are consistent across all tested steering methods.

📄 PDF Abstract BibTeX arXiv:2501.09929

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderLanguage ModelingLanguage ModellingLarge Language Model

Methods 이 논문이 사용한 방법론

Sparse Autoencoder A Sparse Autoencoder is a type of autoencoder that employs sparsity to achieve an information bottleneck. Specifically the loss function is constructed so that activations are…

Similar Papers 제목 키워드 기반

Efficient and accurate steering of Large Language Models through attention-guided feature learning

2026-01-30 · Parmida Davarmanesh, Ashia Wilson, Adityanarayanan Radhakrishnan arxiv

Steering, or direct manipulation of internal activations to guide LLM responses toward specific semantic concepts, is emerging as a promising avenue for both understanding how semantic concepts are stored within LLMs and…

Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection

2026-03-06 · Minjae Kang, Jaehyung Kim arxiv

Large Language Models (LLMs), despite advances in instruction tuning, often fail to follow complex user instructions. Activation steering techniques aim to mitigate this by manipulating model internals, but have a potent…

Instruction Following

UniSteer: Text-Guided Flow Matching in Activation Space for Versatile LLM Steering

2026-05-28 · Yingdong Shi, Ruiming Zhang, Changming Li, Zhiyu Yang 외 arxiv

Activation-based control steers large language models (LLMs) by intervening on their internal representations during inference, and has emerged as an effective paradigm for controlling behaviors such as persona and style…

Instruction Following

Manifold-Guided Attention Steering

2026-05-20 · Ian Li, Kapilesh Guruprasad, Raunak Sengupta, Ninad Satish 외 arxiv

Large language models frequently produce errors in reasoning tasks despite possessing the underlying knowledge required for correct reasoning. One possible approach to improve reasoning consistency is through activation …

Mathematical ReasoningCode Generation

ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment

2026-02-19 · Hongjue Zhao, Haosen Sun, Jiangtao Kong, Xiaochang Li 외 arxiv

Activation steering, or representation engineering, offers a lightweight approach to align large language models (LLMs) by manipulating their internal activations at inference time. However, current methods suffer from t…