Attribute-Based Activation Steering of LLMs for Group-Specific Explanation Generation

• URL: http://arxiv.org/abs/2608.29215v2
• Date: Tue, 01 Sep 2026 07:35:44 GMT
• Title: Attribute-Based Activation Steering of LLMs for Group-Specific Explanation Generation
• Abstract summary: We propose an approach that first identifies group-specific attributes in terms of explanatory style and knowledge of a specific target group.<n>In experiments, we assess the steering effectiveness in terms of specificity and factuality of the generated explanations.
• Score: 12.009555264358182
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: To effectively enable people to understand new topics, explanations should be tailored to their backgrounds and abilities. Prompting alone has been shown to be insufficient for creating such explanations, and other computational methods are missing so far. Therefore, this paper investigates whether LLMs can be steered to generate explanations that are tailored to a specific group of people. To this end, we propose an approach that first identifies group-specific attributes in terms of explanatory style and knowledge of a specific target group. Building on activation engineering, it then computes attribute-based steering vectors and adds them to the internal activations of an LLM during inference to enable a fine-grained steering. In our experiments, we assess the steering effectiveness in terms of specificity and factuality of the generated explanations. Additionally, we evaluate the explanations in a study with human experts from different target groups. Compared to prompting and state-of-the-art steering baselines, our approach tailors the explanations significantly better to the target group while maintaining the best specificity-factuality balance.

Related papers

• Cluster-R1: Large Reasoning Models Are Instruction-following Clustering Agents [81.79110139097297]
  General-purpose embedding models excel at recognizing semantic similarities but fail to capture the characteristics of texts specified by user instructions.<n>We reframe instruction-following clustering as a generative task and train large reasoning models as autonomous clustering agents.<n>Our reasoning-driven training pipeline enables LRMs to interpret high-level clustering instructions and then infer the corresponding latent groupings.
  arXiv  Detail & Related papers  (2026-03-06T10:15:54Z)
• From latent factors to language: a user study on LLM-generated explanations for an inherently interpretable matrix-based recommender system [8.280161440212504]
  We investigate whether large language models (LLMs) can generate effective, user-facing explanations from a mathematically interpretable recommendation model.<n>We conduct a study with 326 participants who assessed the quality of the explanations across five key dimensions.<n>Our analysis reveals that all explanation types are generally well received, with moderate statistical differences between strategies.
  arXiv  Detail & Related papers  (2025-09-23T13:30:03Z)
• Latent Factor Models Meets Instructions: Goal-conditioned Latent Factor Discovery without Task Supervision [50.45597801390757]
  Instruct-LF is a goal-oriented latent factor discovery system.<n>It integrates instruction-following ability with statistical models to handle noisy datasets.
  arXiv  Detail & Related papers  (2025-02-21T02:03:08Z)
• Find the Intention of Instruction: Comprehensive Evaluation of Instruction Understanding for Large Language Models [8.020688053947547]
  One of the key strengths of Large Language Models (LLMs) is their ability to interact with humans by generating appropriate responses to given instructions.<n>This ability, known as instruction-following capability, has established a foundation for the use of LLMs across various fields.<n>We have noted that LLMs can become easily distracted by instruction-formatted statements, which may lead to an oversight of their instruction comprehension skills.
  arXiv  Detail & Related papers  (2024-12-27T04:37:39Z)
• CohEx: A Generalized Framework for Cohort Explanation [5.269665407562217]
  Cohort explanations offer insights into the explainee's behavior on a specific group or cohort of instances.<n>In this paper, we discuss the unique challenges and opportunities associated with measuring cohort explanations.
  arXiv  Detail & Related papers  (2024-10-17T03:36:18Z)
• Local Explanations and Self-Explanations for Assessing Faithfulness in black-box LLMs [1.03590082373586]
  This paper introduces a novel task to assess the faithfulness of large language models (LLMs) using local perturbations and self-explanations. We propose a new efficient alternative explainability technique, inspired by the commonly used leave-one-out approach.
  arXiv  Detail & Related papers  (2024-09-18T10:16:45Z)
• Evaluating Human Alignment and Model Faithfulness of LLM Rationale [66.75309523854476]
  We study how well large language models (LLMs) explain their generations through rationales. We show that prompting-based methods are less "faithful" than attribution-based explanations.
  arXiv  Detail & Related papers  (2024-06-28T20:06:30Z)
• Properties and Challenges of LLM-Generated Explanations [3.257973235065581]
  We study the self-rationalising capabilities of large language models (LLMs) We find that generated explanations show selectivity and contain illustrative elements, but less frequently are subjective or misleading. In particular, we outline positive and negative implications depending on the goals and user groups of the self-rationalising system.
  arXiv  Detail & Related papers  (2024-02-16T09:37:54Z)
• Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Models [54.21695754082441]
  We propose a framework to teach Large Language Models (LLMs) to generate explainable stock predictions. A reflective agent learns how to explain past stock movements through self-reasoning, while the PPO trainer trains the model to generate the most likely explanations. Our framework can outperform both traditional deep-learning and LLM methods in prediction accuracy and Matthews correlation coefficient.
  arXiv  Detail & Related papers  (2024-02-06T03:18:58Z)
• Simple Linguistic Inferences of Large Language Models (LLMs): Blind Spots and Blinds [59.71218039095155]
  We evaluate language understanding capacities on simple inference tasks that most humans find trivial. We target (i) grammatically-specified entailments, (ii) premises with evidential adverbs of uncertainty, and (iii) monotonicity entailments. The models exhibit moderate to low performance on these evaluation sets.
  arXiv  Detail & Related papers  (2023-05-24T06:41:09Z)
• Complementary Explanations for Effective In-Context Learning [77.83124315634386]
  Large language models (LLMs) have exhibited remarkable capabilities in learning from explanations in prompts. This work aims to better understand the mechanisms by which explanations are used for in-context learning.
  arXiv  Detail & Related papers  (2022-11-25T04:40:47Z)

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.