paper-with-me

홈 › Papers

LMs as Task-Specific Knowledge Bases: An Interpretability Analysis

2026-06-25 · Amit Elhelo, Amir Globerson, Mor Geva arxiv

Language models (LMs) capture large amounts of factual knowledge applicable to a wide range of tasks, motivating the view of their parameters as a knowledge base. An important property of knowledge bases is that different queries for the same fact return consistent results, drawing on a single source of truth. We investigate whether LMs satisfy this property through behavioral and mechanistic analyses. Our results suggest that they encode knowledge in a task-specific manner. Behaviorally, facts acquired on one task frequently fail to co-emerge on others during training. Parameter localization experiments suggest a mechanistic explanation, revealing distinct parameter subsets underlying different tasks for the same fact. Finally, we show that chain-of-thought reasoning draws part of its effectiveness from engaging task-specific parameters beyond those tied to the evaluation task. Our findings suggest that what the model knows and how it is asked are intertwined in parameter space, undermining the "knowledge base" analogy and carrying implications for the reliability and controllability of factual knowledge in LMs.

📄 PDF Abstract BibTeX arXiv:2606.27237

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

No Black Boxes: Interpretable and Interactable Predictive Healthcare with Knowledge-Enhanced Agentic Causal Discovery

2025-05-22 · Xiaoxue Han, Pengfei Hu, Jun-En Ding, Chang Lu 외

Deep learning models trained on extensive Electronic Health Records (EHR) data have achieved high accuracy in diagnosis prediction, offering the potential to assist clinicians in decision-making and treatment planning. H…

Causal DiscoveryDecision Making

Decoupling Knowledge and Reasoning in Transformers: A Modular Architecture with Generalized Cross-Attention

2025-01-01 · Zhenyu Guo, WenGuang Chen

Transformers have achieved remarkable success across diverse domains, but their monolithic architecture presents challenges in interpretability, adaptability, and scalability. This paper introduces a novel modular Transf…

Retrieval

Leveraging Wikipedia Navigational Templates for Curating Domain-Specific Fuzzy Conceptual Bases

2021-06-01 · NAACL (DaSH) 2021 6 · Krati Saxena, Tushita Singh, Ashwini Patil, Sagar Sunkle 외

Domain-specific conceptual bases use key concepts to capture domain scope and relevant information. Conceptual bases serve as a foundation for various downstream tasks, including ontology construction, information mappin…

ArticlesKnowledge Graphs

Interpretable Question Answering on Knowledge Bases and Text

2019-06-26 · ACL 2019 7 · Alona Sydorova, Nina Poerner, Benjamin Roth

Interpretability of machine learning (ML) models becomes more relevant with their increasing adoption. In this work, we address the interpretability of ML based question answering (QA) models on a combination of knowledg…

Question Answering

DegreEmbed: incorporating entity embedding into logic rule learning for knowledge graph reasoning

2021-12-18 · Haotian Li, Hongri Liu, Yao Wang, Guodong Xin 외

Knowledge graphs (KGs), as structured representations of real world facts, are intelligent databases incorporating human knowledge that can help machine imitate the way of human problem solving. However, KGs are usually …

Knowledge GraphsLink PredictionQuestion AnsweringRecommendation Systems