Causal Interventions on Continuous Variables: A Case Study on Verb Bias in Steering Vectors for In-Context Learning

• URL: http://arxiv.org/abs/2605.29971v1
• Date: Thu, 28 May 2026 14:09:18 GMT
• Title: Causal Interventions on Continuous Variables: A Case Study on Verb Bias in Steering Vectors for In-Context Learning
• Abstract summary: We introduce a method for causal intervention on continuous variables.<n>We apply this method to a continuous feature that is well-studied in psycholinguistics, namely verb bias.<n>We show that verb bias is causally represented in steering vectors extracted from large language models.
• Score: 7.320379735876713
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Causal interventions in language model representations have largely targeted discrete features, like grammatical number. However, language models must also make use of features that are graded. We introduce a method for causal intervention on continuous variables: given activation vectors paired with a graded target variable, we localize a low-dimensional direction for that variable and use this direction to edit a vectors toward counterfactual target values. We apply this method to a continuous feature that is well-studied in psycholinguistics, namely verb bias (which reflects which syntactic structures tend to follow a given verb). We show that verb bias is causally represented in steering vectors extracted from large language models: counterfactual edits to verb bias systematically shift downstream structural preferences. Verb bias has also previously been linked to in-context learning; in further analyses, we find that steering vectors encode error signals that could drive the error-driven update behavior seen in in-context learning but that these aspects of the steering vectors are not causally used in downstream production. Overall, these results show causal interventions can be applied to continuous variables, though connecting continuous variables to in-context learning remains a challenge.

Related papers

• The Illusion of Robustness: Aggregate Accuracy Hides Prediction Flips under Task-Irrelevant Context [76.36635039699112]
  Large language models (LLMs) are increasingly deployed in context-rich settings where task inputs are often accompanied by long, partially irrelevant context.<n>We find that state-of-the-art models often appear robust to task-irrelevant context at the aggregate level.<n>This aggregate stability, however, masks significant per-example instability.
  arXiv  Detail & Related papers  (2026-07-14T17:01:12Z)
• Causally Evaluating the Learnability of Formal Language Tasks [59.73001113068827]
  We rigorously investigate the relationship between data frequency and learnability.<n>We derive Kullback-Leibler divergence metrics to measure the learnability of specific sub-tasks.<n>Our experiments show that evaluating learnability without causal intervention leads to incorrect conclusions.
  arXiv  Detail & Related papers  (2026-06-08T17:58:36Z)
• Understanding Unreliability of Steering Vectors in Language Models: Geometric Predictors and the Limits of Linear Approximations [0.0]
  I investigate why steering reliability differs across behaviors and how it is impacted by steering vector training data.<n>I find that higher cosine similarity between training activation differences predicts more reliable steering.<n>I observe that behavior datasets where positive and negative activations are better separated along the steering direction are more reliably steerable.
  arXiv  Detail & Related papers  (2026-02-19T22:37:05Z)
• When Models Examine Themselves: Vocabulary-Activation Correspondence in Self-Referential Processing [0.0]
  We show that self-referential vocabulary tracks concurrent activation dynamics.<n>We identify a direction in activation space that distinguishes self-referential from descriptive processing.<n>Findings indicate that self-report in transformer models can, under appropriate conditions, reliably track internal computational states.
  arXiv  Detail & Related papers  (2026-02-11T20:44:33Z)
• When Does Context Help? Error Dynamics of Contextual Information in Large Language Models [64.88201012057822]
  We present a unified theoretical framework for analyzing the effect of arbitrary contextual information in large language models.<n>Our analysis characterizes contextual influence through output error dynamics.<n> Experiments across ICL, retrieval-augmented generation, and memory evolution validate our theory and motivate a principled context selection strategy.
  arXiv  Detail & Related papers  (2026-02-09T05:58:41Z)
• Counterfactual reasoning: an analysis of in-context emergence [57.118735341305786]
  We show that language models are capable of counterfactual reasoning.<n>We find that self-attention, model depth and pre-training data diversity drive performance.<n>Our findings extend to counterfactual reasoning under SDE dynamics.
  arXiv  Detail & Related papers  (2025-06-05T16:02:07Z)
• Activation Scaling for Steering and Interpreting Language Models [55.59689963561315]
  We argue that successfully intervening on a model is a prerequisite for interpreting its internal workings. We establish a three-term objective: a successful intervention should flip the correct with the wrong token and vice versa. Using gradient-based optimization, this objective lets us learn (and later evaluate) a specific kind of efficient and interpretable intervention.
  arXiv  Detail & Related papers  (2024-10-07T12:01:32Z)
• Words in Motion: Extracting Interpretable Control Vectors for Motion Transformers [1.1510009152620668]
  Transformer-based models generate hidden states that are difficult to interpret.<n>We analyze hidden states and modify them at inference, with a focus on motion forecasting.
  arXiv  Detail & Related papers  (2024-06-17T15:07:55Z)
• Backpack Language Models [108.65930795825416]
  We present Backpacks, a new neural architecture that marries strong modeling performance with an interface for interpretability and control. We find that, after training, sense vectors specialize, each encoding a different aspect of a word. We present simple algorithms that intervene on sense vectors to perform controllable text generation and debiasing.
  arXiv  Detail & Related papers  (2023-05-26T09:26:23Z)
• Shapley Head Pruning: Identifying and Removing Interference in Multilingual Transformers [54.4919139401528]
  We show that it is possible to reduce interference by identifying and pruning language-specific parameters. We show that removing identified attention heads from a fixed model improves performance for a target language on both sentence classification and structural prediction.
  arXiv  Detail & Related papers  (2022-10-11T18:11:37Z)
• 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)
• Improving Robustness by Augmenting Training Sentences with Predicate-Argument Structures [62.562760228942054]
  Existing approaches to improve robustness against dataset biases mostly focus on changing the training objective. We propose to augment the input sentences in the training data with their corresponding predicate-argument structures. We show that without targeting a specific bias, our sentence augmentation improves the robustness of transformer models against multiple biases.
  arXiv  Detail & Related papers  (2020-10-23T16:22:05Z)

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.