Multi-Domain Explainability of Preferences

• URL: http://arxiv.org/abs/2505.20088v2
• Date: Thu, 29 May 2025 15:47:53 GMT
• Title: Multi-Domain Explainability of Preferences
• Authors: Nitay Calderon, Liat Ein-Dor, Roi Reichart,
• Abstract summary: We propose a fully automated method for generating concept-based explanations of preferences across multiple domains.<n>Our method utilizes an LLM to identify concepts that distinguish between chosen and rejected responses.<n>Our method achieves strong preference prediction performance, outperforming baselines while also being explainable.
• Score: 20.543061089533673
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Preference mechanisms, such as human preference, LLM-as-a-Judge (LaaJ), and reward models, are central to aligning and evaluating large language models (LLMs). Yet, the underlying concepts that drive these preferences remain poorly understood. In this work, we propose a fully automated method for generating local and global concept-based explanations of preferences across multiple domains. Our method utilizes an LLM to identify concepts that distinguish between chosen and rejected responses, and to represent them with concept-based vectors. To model the relationships between concepts and preferences, we propose a white-box Hierarchical Multi-Domain Regression model that captures both domain-general and domain-specific effects. To evaluate our method, we curate a dataset spanning eight challenging and diverse domains and explain twelve mechanisms. Our method achieves strong preference prediction performance, outperforming baselines while also being explainable. Additionally, we assess explanations in two application-driven settings. First, guiding LLM outputs with concepts from LaaJ explanations yields responses that those judges consistently prefer. Second, prompting LaaJs with concepts explaining humans improves their preference predictions. Together, our work establishes a new paradigm for explainability in the era of LLMs.

Related papers

• Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignment [74.25832963097658]
  Multi-Objective Alignment (MOA) aims to align responses with multiple human preference objectives.<n>We find that DPO-based MOA approaches suffer from widespread preference conflicts in the data.
  arXiv  Detail & Related papers  (2025-02-20T08:27:00Z)
• Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness [27.43137305486112]
  We propose a novel Self-supervised Preference Optimization (SPO) framework, which constructs a self-supervised preference degree loss combined with the alignment loss. The results demonstrate that SPO can be seamlessly integrated with existing preference optimization methods to achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-09-26T12:37:26Z)
• DEAL: Disentangle and Localize Concept-level Explanations for VLMs [10.397502254316645]
  Large pre-trained Vision-Language Models might not be able to identify fine-grained concepts. We propose to DisEnt and Localize (Angle) concept-level explanations for concepts without human annotations. Our empirical results demonstrate that the proposed method significantly improves the concept-level explanations of the model in terms of disentanglability and localizability.
  arXiv  Detail & Related papers  (2024-07-19T15:39:19Z)
• Sparsity-Guided Holistic Explanation for LLMs with Interpretable Inference-Time Intervention [53.896974148579346]
  Large Language Models (LLMs) have achieved unprecedented breakthroughs in various natural language processing domains. The enigmatic black-box'' nature of LLMs remains a significant challenge for interpretability, hampering transparent and accountable applications. We propose a novel methodology anchored in sparsity-guided techniques, aiming to provide a holistic interpretation of LLMs.
  arXiv  Detail & Related papers  (2023-12-22T19:55:58Z)
• RecExplainer: Aligning Large Language Models for Explaining Recommendation Models [50.74181089742969]
  Large language models (LLMs) have demonstrated remarkable intelligence in understanding, reasoning, and instruction following. This paper presents the initial exploration of using LLMs as surrogate models to explain black-box recommender models. To facilitate an effective alignment, we introduce three methods: behavior alignment, intention alignment, and hybrid alignment.
  arXiv  Detail & Related papers  (2023-11-18T03:05:43Z)
• Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals [67.64770842323966]
  Causal explanations of predictions of NLP systems are essential to ensure safety and establish trust. Existing methods often fall short of explaining model predictions effectively or efficiently. We propose two approaches for counterfactual (CF) approximation.
  arXiv  Detail & Related papers  (2023-10-01T07:31:04Z)
• Evaluating and Explaining Large Language Models for Code Using Syntactic Structures [74.93762031957883]
  This paper introduces ASTxplainer, an explainability method specific to Large Language Models for code. At its core, ASTxplainer provides an automated method for aligning token predictions with AST nodes. We perform an empirical evaluation on 12 popular LLMs for code using a curated dataset of the most popular GitHub projects.
  arXiv  Detail & Related papers  (2023-08-07T18:50:57Z)
• Concept-Centric Transformers: Enhancing Model Interpretability through Object-Centric Concept Learning within a Shared Global Workspace [1.6574413179773757]
  Concept-Centric Transformers is a simple yet effective configuration of the shared global workspace for interpretability. We show that our model achieves better classification accuracy than all baselines across all problems.
  arXiv  Detail & Related papers  (2023-05-25T06:37:39Z)
• An Additive Instance-Wise Approach to Multi-class Model Interpretation [53.87578024052922]
  Interpretable machine learning offers insights into what factors drive a certain prediction of a black-box system. Existing methods mainly focus on selecting explanatory input features, which follow either locally additive or instance-wise approaches. This work exploits the strengths of both methods and proposes a global framework for learning local explanations simultaneously for multiple target classes.
  arXiv  Detail & Related papers  (2022-07-07T06:50:27Z)
• CARE: Coherent Actionable Recourse based on Sound Counterfactual Explanations [0.0]
  This paper introduces CARE, a modular explanation framework that addresses the model- and user-level desiderata. As a model-agnostic approach, CARE generates multiple, diverse explanations for any black-box model.
  arXiv  Detail & Related papers  (2021-08-18T15:26:59Z)
• Multi-Objective Counterfactual Explanations [0.7349727826230864]
  We propose the Multi-Objective Counterfactuals (MOC) method, which translates the counterfactual search into a multi-objective optimization problem. Our approach not only returns a diverse set of counterfactuals with different trade-offs between the proposed objectives, but also maintains diversity in feature space.
  arXiv  Detail & Related papers  (2020-04-23T13:56:39Z)

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.