Steering Risk Preferences in Large Language Models by Aligning Behavioral and Neural Representations

• URL: http://arxiv.org/abs/2505.11615v1
• Date: Fri, 16 May 2025 18:23:10 GMT
• Title: Steering Risk Preferences in Large Language Models by Aligning Behavioral and Neural Representations
• Authors: Jian-Qiao Zhu, Haijiang Yan, Thomas L. Griffiths,
• Abstract summary: We propose a principled approach for uncovering steering vectors.<n>We focus on extracting latent risk preferences from large language models.<n>We show that the resulting steering vectors successfully and reliably modulate LLM outputs in line with the targeted behavior.
• Score: 4.029252551781513
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Changing the behavior of large language models (LLMs) can be as straightforward as editing the Transformer's residual streams using appropriately constructed "steering vectors." These modifications to internal neural activations, a form of representation engineering, offer an effective and targeted means of influencing model behavior without retraining or fine-tuning the model. But how can such steering vectors be systematically identified? We propose a principled approach for uncovering steering vectors by aligning latent representations elicited through behavioral methods (specifically, Markov chain Monte Carlo with LLMs) with their neural counterparts. To evaluate this approach, we focus on extracting latent risk preferences from LLMs and steering their risk-related outputs using the aligned representations as steering vectors. We show that the resulting steering vectors successfully and reliably modulate LLM outputs in line with the targeted behavior.

Related papers

• GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs [56.93583799109029]
  GrAInS is an inference-time steering approach that operates across both language-only and vision-language models and tasks.<n>During inference, GrAInS hidden activations at transformer layers guided by token-level attribution signals, and normalizes activations to preserve representational scale.<n>It consistently outperforms both fine-tuning and existing steering baselines.
  arXiv  Detail & Related papers  (2025-07-24T02:34:13Z)
• Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models [50.19188692497892]
  Traditional alignment methods often require retraining large pretrained models.<n>We propose a novel textitResidual Alignment Model (textitRAM) that formalizes the alignment process as a type of importance sampling.<n>We develop a resampling algorithm with iterative token-level decoding to address the common first-token latency issue in comparable methods.
  arXiv  Detail & Related papers  (2025-05-26T08:53:02Z)
• 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)
• On the Limitations of Steering in Language Model Alignment [10.014248704653]
  We propose a framework to assess the limitations of steering vectors as alignment mechanisms.<n>Using a framework of transformer hook interventions and antonym-based function vectors, we evaluate the role of prompt structure and context complexity in steering effectiveness.
  arXiv  Detail & Related papers  (2025-05-02T10:08:34Z)
• Improving Reasoning Performance in Large Language Models via Representation Engineering [2.0099933815960256]
  We propose a representation engineering approach for large language models (LLMs)<n>Model activations are read from the residual stream of an LLM when processing a reasoning task.<n>We show that an LLM can, to a certain degree, be controlled to improve its perceived reasoning ability by modulating activations.
  arXiv  Detail & Related papers  (2025-04-28T04:58:43Z)
• Investigating Generalization of One-shot LLM Steering Vectors [21.2431937128876]
  We propose optimizing steering vectors through gradient descent on a single training example.<n>We find that the resulting vectors effectively mediate safety-relevant behaviors in multiple models.
  arXiv  Detail & Related papers  (2025-02-26T06:13:01Z)
• Improving Instruction-Following in Language Models through Activation Steering [58.876600545898675]
  We derive instruction-specific vector representations from language models and use them to steer models accordingly.<n>We demonstrate how this method can enhance model adherence to constraints such as output format, length, and word inclusion.<n>Our findings demonstrate that activation steering offers a practical and scalable approach for fine-grained control in language generation.
  arXiv  Detail & Related papers  (2024-10-15T08:38:20Z)
• Steering Without Side Effects: Improving Post-Deployment Control of Language Models [61.99293520621248]
  Language models (LMs) have been shown to behave unexpectedly post-deployment. We present KL-then-steer (KTS), a technique that decreases the side effects of steering while retaining its benefits. Our best method prevents 44% of jailbreak attacks compared to the original Llama-2-chat-7B model.
  arXiv  Detail & Related papers  (2024-06-21T01:37:39Z)
• 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)
• Extracting Latent Steering Vectors from Pretrained Language Models [14.77762401765532]
  We show that latent vectors can be extracted directly from language model decoders without fine-tuning. Experiments show that there exist steering vectors, which, when added to the hidden states of the language model, generate a target sentence nearly perfectly. We find that distances between steering vectors reflect sentence similarity when evaluated on a textual similarity benchmark.
  arXiv  Detail & Related papers  (2022-05-10T19:04:37Z)
• Decision Transformer: Reinforcement Learning via Sequence Modeling [102.86873656751489]
  We present a framework that abstracts Reinforcement Learning (RL) as a sequence modeling problem. We present Decision Transformer, an architecture that casts the problem of RL as conditional sequence modeling. Despite its simplicity, Decision Transformer matches or exceeds the performance of state-of-the-art offline RL baselines on Atari, OpenAI Gym, and Key-to-Door tasks.
  arXiv  Detail & Related papers  (2021-06-02T17:53:39Z)

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.