Steering Conceptual Bias via Transformer Latent-Subspace Activation

• URL: http://arxiv.org/abs/2506.18887v1
• Date: Mon, 23 Jun 2025 17:56:34 GMT
• Title: Steering Conceptual Bias via Transformer Latent-Subspace Activation
• Authors: Vansh Sharma, Venkat Raman,
• Abstract summary: This work examines whether activating latent subspaces in language models (LLMs) can steer scientific code generation toward a specific programming language.<n>A neuron-attribution method, perturbing the highest activated static weight for a C++ or CPP token, proved brittle and exhibited limited generalization.<n>A gradient-refined adaptive activation steering framework (G-ACT) was developed.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: This work examines whether activating latent subspaces in language models (LLMs) can steer scientific code generation toward a specific programming language. Five causal LLMs were first evaluated on scientific coding prompts to quantify their baseline bias among four programming languages. A static neuron-attribution method, perturbing the highest activated MLP weight for a C++ or CPP token, proved brittle and exhibited limited generalization across prompt styles and model scales. To address these limitations, a gradient-refined adaptive activation steering framework (G-ACT) was developed: per-prompt activation differences are clustered into a small set of steering directions, and lightweight per-layer probes are trained and refined online to select the appropriate steering vector. In LLaMA-3.2 3B, this approach reliably biases generation towards the CPP language by increasing the average probe classification accuracy by 15% and the early layers (0-6) improving the probe classification accuracy by 61.5% compared to the standard ACT framework. For LLaMA-3.3 70B, where attention-head signals become more diffuse, targeted injections at key layers still improve language selection. Although per-layer probing introduces a modest inference overhead, it remains practical by steering only a subset of layers and enables reproducible model behavior. These results demonstrate a scalable, interpretable and efficient mechanism for concept-level control for practical agentic systems.

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)
• 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)
• Patterns and Mechanisms of Contrastive Activation Engineering [0.374490703387131]
  CAE has the potential to introduce a new paradigm of flexible, task-specific behavior tuning.<n>We analyze the performance of CAE in in in-distribution, out-of-distribution settings, evaluate drawbacks, and begin to develop comprehensive guidelines for its effective deployment.
  arXiv  Detail & Related papers  (2025-05-06T05:15:12Z)
• R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference [77.47238561728459]
  R-Sparse is a training-free activation sparsity approach capable of achieving high sparsity levels in advanced LLMs.<n> Experiments on Llama-2/3 and Mistral models across ten diverse tasks demonstrate that R-Sparse achieves comparable performance at 50% model-level sparsity.
  arXiv  Detail & Related papers  (2025-04-28T03:30:32Z)
• 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)
• Joint Localization and Activation Editing for Low-Resource Fine-Tuning [73.64004083269424]
  We propose a joint localization and activation editing (JoLA) method.<n>JoLA learns (1) which heads in the Transformer to edit (2) whether the intervention should be additive, multiplicative, or both and (3) the intervention parameters themselves.<n>We demonstrate that JoLA consistently outperforms existing methods.
  arXiv  Detail & Related papers  (2025-02-03T09:13:09Z)
• Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning [73.73967342609603]
  We introduce a predictor-corrector learning framework to minimize truncation errors. We also propose an exponential moving average-based coefficient learning method to strengthen our higher-order predictor. Our model surpasses a robust 3.8B DeepNet by an average of 2.9 SacreBLEU, using only 1/3 parameters.
  arXiv  Detail & Related papers  (2024-11-05T12:26:25Z)
• GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation [108.2008975785364]
  Graph Inspired Veracity Extrapolation (GIVE) is a novel reasoning method that merges parametric and non-parametric memories to improve accurate reasoning with minimal external input.<n>GIVE guides the LLM agent to select the most pertinent expert data (observe), engage in query-specific divergent thinking (reflect), and then synthesize this information to produce the final output (speak)
  arXiv  Detail & Related papers  (2024-10-11T03:05:06Z)
• Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models [31.509994889286183]
  We introduce Language Agent Tree Search (LATS) -- the first general framework that synergizes the capabilities of language models (LMs) in reasoning, acting, and planning. A key feature of our approach is the incorporation of an environment for external feedback, which offers a more deliberate and adaptive problem-solving mechanism. LATS achieves state-of-the-art pass@1 accuracy (92.7%) for programming on HumanEval with GPT-4 and demonstrates gradient-free performance (average score of 75.9) comparable to gradient-based fine-tuning for web navigation on WebShop with GPT
  arXiv  Detail & Related papers  (2023-10-06T17:55:11Z)
• Latency Adjustable Transformer Encoder for Language Understanding [0.8287206589886879]
  This paper proposes an efficient Transformer architecture that adjusts the inference computational cost adaptively with a desired inference latency speedup. The proposed method detects less important hidden sequence elements (word-vectors) and eliminates them in each encoder layer using a proposed Attention Context Contribution (ACC) metric. The proposed method mathematically and experimentally improves the inference latency of BERT_base and GPT-2 by up to 4.8 and 3.72 times with less than 0.75% accuracy drop and passable perplexity on average.
  arXiv  Detail & Related papers  (2022-01-10T13:04:39Z)
• Layer-adaptive sparsity for the Magnitude-based Pruning [88.37510230946478]
  We propose a novel importance score for global pruning, coined layer-adaptive magnitude-based pruning (LAMP) score. LAMP consistently outperforms popular existing schemes for layerwise sparsity selection.
  arXiv  Detail & Related papers  (2020-10-15T09:14:02Z)
• GeDi: Generative Discriminator Guided Sequence Generation [53.15651536569169]
  We propose GeDi as an efficient method for using smaller LMs as generative discriminators to guide generation from large LMs. We find that GeDi gives stronger controllability than the state of the art method while also achieving generation speeds more than 30 times faster.
  arXiv  Detail & Related papers  (2020-09-14T17:45:36Z)

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.