SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models

• URL: http://arxiv.org/abs/2505.16188v1
• Date: Thu, 22 May 2025 03:46:57 GMT
• Title: SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models
• Authors: Zirui He, Mingyu Jin, Bo Shen, Ali Payani, Yongfeng Zhang, Mengnan Du,
• Abstract summary: Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation.<n>This paper introduces a novel supervised steering approach that operates in sparse, interpretable representation spaces.
• Score: 41.553639748766784
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but controlling their behavior reliably remains challenging, especially in open-ended generation settings. This paper introduces a novel supervised steering approach that operates in sparse, interpretable representation spaces. We employ sparse autoencoders (SAEs)to obtain sparse latent representations that aim to disentangle semantic attributes from model activations. Then we train linear classifiers to identify a small subspace of task-relevant dimensions in latent representations. Finally, we learn supervised steering vectors constrained to this subspace, optimized to align with target behaviors. Experiments across sentiment, truthfulness, and politics polarity steering tasks with multiple LLMs demonstrate that our supervised steering vectors achieve higher success rates with minimal degradation in generation quality compared to existing methods. Further analysis reveals that a notably small subspace is sufficient for effective steering, enabling more targeted and interpretable interventions.

Related papers

• ExpertSteer: Intervening in LLMs through Expert Knowledge [71.12193680015622]
  Activation steering offers a promising method to control the generation process of Large Language Models.<n>We propose ExpertSteer, a novel approach that leverages arbitrary specialized expert models to generate steering vectors.<n>We conduct comprehensive experiments using three LLMs on 15 popular benchmarks across four distinct domains.
  arXiv  Detail & Related papers  (2025-05-18T08:55:46Z)
• Towards LLM Guardrails via Sparse Representation Steering [11.710399901426873]
  Large Language Models (LLMs) have demonstrated remarkable performance in natural language generation tasks.<n>We propose a sparse encoding-based representation engineering method, named SRE, which decomposes polysemantic activations into a structured, monosemantic feature space.<n>By leveraging sparse autoencoding, our approach isolates and adjusts only task-specific sparse feature dimensions, enabling precise and interpretable steering of model behavior.
  arXiv  Detail & Related papers  (2025-03-21T04:50:25Z)
• Navigating Motion Agents in Dynamic and Cluttered Environments through LLM Reasoning [69.5875073447454]
  This paper advances motion agents empowered by large language models (LLMs) toward autonomous navigation in dynamic and cluttered environments.<n>Our training-free framework supports multi-agent coordination, closed-loop replanning, and dynamic obstacle avoidance without retraining or fine-tuning.
  arXiv  Detail & Related papers  (2025-03-10T13:39:09Z)
• Steering Large Language Model Activations in Sparse Spaces [21.55545768931058]
  A key challenge in AI alignment is guiding large language models (LLMs) to follow desired behaviors at test time.<n>We introduce sparse activation steering (SAS), a method that leverages sparse autoencoders (SAEs) to steer behavior in sparse spaces.
  arXiv  Detail & Related papers  (2025-02-28T20:43:45Z)
• Identifiable Steering via Sparse Autoencoding of Multi-Concept Shifts [11.81523319216474]
  Steering methods manipulate the representations of large language models (LLMs) to induce responses that have desired properties.<n>Traditionally, steering has relied on supervision, such as from contrastive pairs of prompts that vary in a single target concept.<n>We introduce Sparse Shift Autoencoders (SSAEs) that instead map the differences between embeddings to sparse representations.
  arXiv  Detail & Related papers  (2025-02-14T08:49:41Z)
• LF-Steering: Latent Feature Activation Steering for Enhancing Semantic Consistency in Large Language Models [16.37602070339033]
  Large Language Models (LLMs) often generate inconsistent responses when prompted with semantically equivalent paraphrased inputs.<n>We propose LF-Steering, a novel activation steering approach to precisely identify latent feature representations responsible for semantic inconsistency.<n>Our method maps the hidden states of the relevant transformer layer into a sparsely activated, high-dimensional feature space based on a sparse autoencoder.
  arXiv  Detail & Related papers  (2025-01-19T13:06:51Z)
• MALMM: Multi-Agent Large Language Models for Zero-Shot Robotics Manipulation [52.739500459903724]
  Large Language Models (LLMs) have demonstrated remarkable planning abilities across various domains, including robotics manipulation and navigation. We propose a novel multi-agent LLM framework that distributes high-level planning and low-level control code generation across specialized LLM agents. We evaluate our approach on nine RLBench tasks, including long-horizon tasks, and demonstrate its ability to solve robotics manipulation in a zero-shot setting.
  arXiv  Detail & Related papers  (2024-11-26T17:53:44Z)
• AD-H: Autonomous Driving with Hierarchical Agents [64.49185157446297]
  We propose to connect high-level instructions and low-level control signals with mid-level language-driven commands. We implement this idea through a hierarchical multi-agent driving system named AD-H.
  arXiv  Detail & Related papers  (2024-06-05T17:25:46Z)
• Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization [34.05163996072159]
  "steering vectors" are extracted from the activations of human preference data. This work proposes an innovative approach that could produce more effective steering vectors through bi-directional preference optimization. Our method is designed to allow steering vectors to directly influence the generation probability of contrastive human preference data pairs.
  arXiv  Detail & Related papers  (2024-05-28T05:10:40Z)
• InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance [56.184255657175335]
  We develop textbfInferAligner, a novel inference-time alignment method that utilizes cross-model guidance for harmlessness alignment. Experimental results show that our method can be very effectively applied to domain-specific models in finance, medicine, and mathematics. It significantly diminishes the Attack Success Rate (ASR) of both harmful instructions and jailbreak attacks, while maintaining almost unchanged performance in downstream tasks.
  arXiv  Detail & Related papers  (2024-01-20T10:41:03Z)
• Improve Variational Autoencoder for Text Generationwith Discrete Latent Bottleneck [52.08901549360262]
  Variational autoencoders (VAEs) are essential tools in end-to-end representation learning. VAEs tend to ignore latent variables with a strong auto-regressive decoder. We propose a principled approach to enforce an implicit latent feature matching in a more compact latent space.
  arXiv  Detail & Related papers  (2020-04-22T14:41:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.