REAL: Reading Out Transformer Activations for Precise Localization in Language Model Steering

Li-Ming Zhan, Bo LIU, Yujie Feng, Chengqiang Xie, Jiannong Cao, Xiao-Ming Wu

Keywords: language modeling; representation engineering

Abstract: Inference-time steering aims to alter an LLM’s responses without changing its parameters. A key challenge lies in selecting internal modules that most strongly govern the target behavior; existing approaches often rely on simplistic cues or ad hoc heuristics, leading to suboptimal or unintended effects. In this work, we introduce \modelname{}, a novel framework for identifying behavior-relevant modules (heads or layers) in Transformers. For each module, we train a vector-quantized autoencoder (VQ-AE) on its hidden activations, partitioning the latent space into behavior-relevant and behavior-irrelevant subspaces via a shared, learnable codebook. We quantify each module’s behavioral relevance by evaluating how effectively the VQ-AE encodings distinguish between behavior-aligned and behavior-violating responses using a binary classification metric. This relevance score informs both module selection and steering strength. We evaluate \modelname{} across eight LLMs from two model families (\textsc{Llama} and \textsc{Qwen}) and nine datasets spanning truthfulness enhancement, open-domain question answering under knowledge conflicts, and general alignment tasks. \modelname{} enables more effective inference-time interventions, yielding significant improvements on these steering tasks. Notably, it achieves an average relative improvement of 20\% (up to 81.5\%) over the seminal ITI method~\citep{DBLP:conf/nips/0002PVPW23} on truthfulness steering. Moreover, the modules selected by our method exhibit strong zero-shot generalization in cross-domain truthfulness-steering scenarios.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Submission Number: 464