Inference Time Causal Probing in LLMs

• URL: http://arxiv.org/abs/2605.07631v1
• Date: Fri, 08 May 2026 11:59:13 GMT
• Title: Inference Time Causal Probing in LLMs
• Abstract summary: In causal probing, an intervention modifies hidden states so that a property takes on a different value.<n>We propose Hidden-state Driven Margin Intervention (HDMI), a probe-free, gradient-based technique that directly steers hidden states.<n> HDMI consistently achieves higher reliability than prior methods on the LGD agreement corpus and the CausalGym benchmark.
• Score: 26.69306706280534
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Causal probing methods aim to test and control how internal representations influence the behavior of generative models. In causal probing, an intervention modifies hidden states so that a property takes on a different value. Most existing approaches define such interventions by training an auxiliary probe classifier, which ties the method to a specific task or model and risks misalignment with the model's predictive geometry. We propose Hidden-state Driven Margin Intervention (HDMI), a probe-free, gradient-based technique that directly steers hidden states using the model's native output. HDMI applies a margin objective that increases the probability of a target continuation while decreasing that of the source, without relying on probe classifiers. We further introduce a lookahead variant (LA-HDMI) for text editing that backpropagates through the softmax embeddings, modifying the current hidden state so that the likelihood of user-specified tokens increases in next token generations while preserving fluency. To evaluate interventions, we measure completeness (whether the targeted property changes as intended) and selectivity (whether unrelated properties are preserved), and report their harmonic mean as an overall measure of reliability. HDMI consistently achieves higher reliability than prior methods on the LGD agreement corpus and the CausalGym benchmark, across Meta-Llama-3-8B-Instruct, and Pythia-70M.

Related papers

• CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs [100.38986535324284]
  We introduce textbfCIAware-Bench, a benchmark for measuring textbfcontrol textbfintervention (CI) awareness across frontier models.<n>CIAware-Bench tests whether models can distinguish their own trajectories from those modified by a control intervention.
  arXiv  Detail & Related papers  (2026-06-09T16:24:16Z)
• Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics [42.27928681606673]
  Large Reasoning Models (LRMs) introduce new opportunities for safety monitoring through their Chain of Thought (CoT) reasoning.<n>We investigate the hidden representations of LRMs to determine whether future behavior can be predicted from prompt and CoT representations.<n>We find that future model behavior is more distinguishable when examined over the full trajectory than from a single static prediction.
  arXiv  Detail & Related papers  (2026-05-18T15:29:04Z)
• LiveFMBench: Unveiling the Power and Limits of Agentic Workflows in Specification Generation [75.05397479715576]
  Large language models (LLMs) and agents have shown promising progress, but their true capabilities and failure modes remain unclear.<n>We present the first systematic and contamination-aware study of LLM- and agent-based formal specification generation for C programs.
  arXiv  Detail & Related papers  (2026-05-02T11:31:33Z)
• Steering and Rectifying Latent Representation Manifolds in Frozen Multi-modal LLMs for Video Anomaly Detection [52.5174167737992]
  Video anomaly detection (VAD) aims to identify abnormal events in videos.<n>We propose SteerVAD, which advances MLLM-based VAD by shifting from passively reading to actively steering and rectifying internal representations.<n>Our method achieves state-of-the-art performance among tuning-free approaches requiring only 1% of training data.
  arXiv  Detail & Related papers  (2026-02-27T13:48:50Z)
• Forward Consistency Learning with Gated Context Aggregation for Video Anomaly Detection [17.79982215633934]
  Video anomaly detection (VAD) aims to measure deviations from normal patterns for various events in real-time surveillance systems.<n>Most existing VAD methods rely on large-scale models to pursue extreme accuracy, limiting their feasibility on resource-limited edge devices.<n>We introduce FoGA, a lightweight VAD model that performs Forward consistency learning with Gated context aggregation.
  arXiv  Detail & Related papers  (2026-01-26T04:35:31Z)
• Sample Margin-Aware Recalibration of Temperature Scaling [20.87493013833571]
  Recent advances in deep learning have significantly improved predictive accuracy.<n>Modern neural networks remain systematically overconfident, posing risks for deployment in safety-critical scenarios.<n>We propose a lightweight, data-efficient recalibration method that precisely scales logits based on the margin between the top two logits.
  arXiv  Detail & Related papers  (2025-06-30T03:35:05Z)
• DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation [18.77296551727931]
  We propose DECIDER, a novel approach that leverages priors from large language models (LLMs) and vision-language models (VLMs) to detect failures in image models. DECIDER consistently achieves state-of-the-art failure detection performance, significantly outperforming baselines in terms of the overall Matthews correlation coefficient.
  arXiv  Detail & Related papers  (2024-08-01T07:08:11Z)
• Model Inversion Attacks Through Target-Specific Conditional Diffusion Models [54.69008212790426]
  Model inversion attacks (MIAs) aim to reconstruct private images from a target classifier's training set, thereby raising privacy concerns in AI applications. Previous GAN-based MIAs tend to suffer from inferior generative fidelity due to GAN's inherent flaws and biased optimization within latent space. We propose Diffusion-based Model Inversion (Diff-MI) attacks to alleviate these issues.
  arXiv  Detail & Related papers  (2024-07-16T06:38:49Z)
• Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation [49.827306773992376]
  Continual Test-Time Adaptation (CTTA) is proposed to migrate a source pre-trained model to continually changing target distributions. Our proposed method attains state-of-the-art performance in both classification and segmentation CTTA tasks.
  arXiv  Detail & Related papers  (2023-12-19T15:34:52Z)
• Distributional Shift-Aware Off-Policy Interval Estimation: A Unified Error Quantification Framework [8.572441599469597]
  We study high-confidence off-policy evaluation in the context of infinite-horizon Markov decision processes. The objective is to establish a confidence interval (CI) for the target policy value using only offline data pre-collected from unknown behavior policies. We show that our algorithm is sample-efficient, error-robust, and provably convergent even in non-linear function approximation settings.
  arXiv  Detail & Related papers  (2023-09-23T06:35:44Z)
• MAPS: A Noise-Robust Progressive Learning Approach for Source-Free Domain Adaptive Keypoint Detection [76.97324120775475]
  Cross-domain keypoint detection methods always require accessing the source data during adaptation. This paper considers source-free domain adaptive keypoint detection, where only the well-trained source model is provided to the target domain.
  arXiv  Detail & Related papers  (2023-02-09T12:06:08Z)

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.