Steering When Necessary: Flexible Steering Large Language Models with Backtracking

• URL: http://arxiv.org/abs/2508.17621v2
• Date: Wed, 01 Oct 2025 14:31:05 GMT
• Title: Steering When Necessary: Flexible Steering Large Language Models with Backtracking
• Authors: Zifeng Cheng, Jinwei Gan, Zhiwei Jiang, Cong Wang, Yafeng Yin, Xiang Luo, Yuchen Fu, Qing Gu,
• Abstract summary: Large language models (LLMs) have achieved remarkable performance across many generation tasks.<n> Activation steering is an effective and cost-efficient approach that directly modifies the activations of LLMs during the inference stage.<n>We propose the Flexible Activation Steering with Backtracking (FASB) framework, which dynamically determines both the necessity and strength of intervention.
• Score: 16.23081952791394
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) have achieved remarkable performance across many generation tasks. Nevertheless, effectively aligning them with desired behaviors remains a significant challenge. Activation steering is an effective and cost-efficient approach that directly modifies the activations of LLMs during the inference stage, aligning their responses with the desired behaviors and avoiding the high cost of fine-tuning. Existing methods typically indiscriminately intervene to all generations or rely solely on the question to determine intervention, which limits the accurate assessment of the intervention strength. To this end, we propose the Flexible Activation Steering with Backtracking (FASB) framework, which dynamically determines both the necessity and strength of intervention by tracking the internal states of the LLMs during generation, considering both the question and the generated content. Since intervening after detecting a deviation from the desired behavior is often too late, we further propose the backtracking mechanism to correct the deviated tokens and steer the LLMs toward the desired behavior. Extensive experiments on the TruthfulQA dataset and six multiple-choice datasets demonstrate that our method outperforms baselines. Our code will be released at https://github.com/gjw185/FASB.

Related papers

• On the Paradoxical Interference between Instruction-Following and Task Solving [50.75960598434753]
  Instruction following aims to align Large Language Models (LLMs) with human intent by specifying explicit constraints on how tasks should be performed.<n>We reveal a counterintuitive phenomenon: instruction following can paradoxically interfere with LLMs' task-solving capability.<n>We propose a metric, SUSTAINSCORE, to quantify the interference of instruction following with task solving.
  arXiv  Detail & Related papers  (2026-01-29T17:48:56Z)
• Steering Language Models Before They Speak: Logit-Level Interventions [9.055997973281919]
  We propose a training-free inference-time logit intervention for controllable generation.<n>Our results show that statistically grounded logit steering can achieve large, consistent, and multi-task control gains.
  arXiv  Detail & Related papers  (2026-01-16T03:00:33Z)
• Guiding Giants: Lightweight Controllers for Weighted Activation Steering in LLMs [3.2361985831403404]
  Activation steering provides an alternative for inference-time control.<n>We introduce a novel approach using a lightweight, trainable controller network integrated during inference.
  arXiv  Detail & Related papers  (2025-05-22T01:48:38Z)
• Task-driven Layerwise Additive Activation Intervention [12.152228552335798]
  Modern language models (LMs) have significantly advanced generative modeling in natural language processing (NLP)<n>This paper proposes a layer-wise additive activation intervention framework that optimize the intervention process.<n>We benchmark our framework on various datasets, demonstrating improvements in the accuracy of pre-trained LMs and competing intervention baselines.
  arXiv  Detail & Related papers  (2025-02-10T02:49:46Z)
• Probe-Free Low-Rank Activation Intervention [26.502232859901167]
  Inference-time interventions that edit the hidden activations have shown promising results in steering the LMs towards desirable generations.<n>This paper proposes a probe-free intervention method FLORAIN for all attention heads in a specific activation layer.
  arXiv  Detail & Related papers  (2025-02-06T13:03:05Z)
• Adaptive Distraction: Probing LLM Contextual Robustness with Automated Tree Search [76.54475437069395]
  Large Language Models (LLMs) often struggle to maintain their original performance when faced with semantically coherent but task-irrelevant contextual information.<n>We propose a dynamic distraction generation framework based on tree search, where the generation process is guided by model behavior.
  arXiv  Detail & Related papers  (2025-02-03T18:43:36Z)
• Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors [8.761404991620285]
  Activation intervention has emerged as an effective and economical method to modify the behavior of large language models (LLMs)<n>We propose Semantics-Adaptive Dynamic Intervention (SADI), a novel method that constructs a dynamic steering vector to intervene model activations at inference time.<n> Experimental results show that SADI outperforms established baselines by substantial margins, improving task performance without training.
  arXiv  Detail & Related papers  (2024-10-16T06:58:49Z)
• Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models [104.55763564037831]
  We train a regression model that leverages attention maps, probabilities on the current generation step, and recurrently computed uncertainty scores from previously generated tokens.<n>Our evaluation shows that the proposed method is highly effective for selective generation, achieving substantial improvements over rivaling unsupervised and supervised approaches.
  arXiv  Detail & Related papers  (2024-08-20T09:42:26Z)
• Self-Exploring Language Models: Active Preference Elicitation for Online Alignment [88.56809269990625]
  We propose a bilevel objective optimistically biased towards potentially high-reward responses to actively explore out-of-distribution regions. Our experimental results demonstrate that when fine-tuned on Zephyr-7B-SFT and Llama-3-8B-Instruct models, Self-Exploring Language Models (SELM) significantly boosts the performance on instruction-following benchmarks.
  arXiv  Detail & Related papers  (2024-05-29T17:59:07Z)
• 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)
• Amortizing intractable inference in large language models [56.92471123778389]
  We use amortized Bayesian inference to sample from intractable posterior distributions. We empirically demonstrate that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training. As an important application, we interpret chain-of-thought reasoning as a latent variable modeling problem.
  arXiv  Detail & Related papers  (2023-10-06T16:36:08Z)

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.