Predicate Importance Estimation and Decoupled Rationale-Score Distillation for Entity Alignment

• URL: http://arxiv.org/abs/2606.22992v1
• Date: Mon, 22 Jun 2026 08:11:35 GMT
• Title: Predicate Importance Estimation and Decoupled Rationale-Score Distillation for Entity Alignment
• Abstract summary: We propose two complementary modules: Predicate Importance Estimation (PIE) and Decoupled Rationale-Score Distillation (DRSD)<n>PIE is a compact embedding-based approach that removes the subject information from each 1-hop triple, encodes the resulting subjectless triples, and aggregates them with learnable predicate-importance weights.<n>DRSD enables the SLM to learn task-specific reasoning while retaining a less label-biased confidence signal.
• Score: 14.247246375889262
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Knowledge graphs (KGs) are increasingly used as structured context for Large Language Models (LLMs), but industrial KG-RAG systems often need to integrate public and domain-specific KGs constructed from heterogeneous databases. This integration relies on Entity Alignment (EA), where lexical matching alone is insufficient under predicate-name variation and incomplete local neighborhoods. We address EA for KG integration by constructing a pairwise EA dataset and proposing two complementary modules: Predicate Importance Estimation (PIE) and Decoupled Rationale-Score Distillation (DRSD). PIE is a compact embedding-based approach that removes the subject information from each 1-hop triple, encodes the resulting subjectless triples, and aggregates them with learnable predicate-importance weights to build predicate-aware entity embeddings. DRSD trains a distilled small language model (SLM) with pseudo-answers produced by a teacher LLM through distinct prompts. By converting binary EA labels into text-based supervision and decoupling confidence-score estimation from label-consistent rationales, DRSD enables the SLM to learn task-specific reasoning while retaining a less label-biased confidence signal. Experiments show that PIE and DRSD improve EA classification. Moreover, because DRSD decouples confidence-score estimation from the decision, a discrepancy between the two flags an uncertain prediction for human review, thereby enabling a practical discrepancy between automatic acceptance and human-in-the-loop verification.

Related papers

• CONSISTRE: A Unified Consistency-Aware Framework for Document-Level Relation Extraction with Large Language Models [11.083514956613383]
  Document-level relation extraction (DocRE) aims to extract relations among multiple entities across extended contexts.<n>Large language models (LLMs) show remarkable reasoning capabilities in information extraction.<n>LLMs may violate fundamental relational constraints such as transitivity, symmetry, and functional uniqueness, leading to contradictory and unreliable outputs.<n>We propose a unified consistency-aware framework for DocRE that addresses this limitation through two complementary tracks.
  arXiv  Detail & Related papers  (2026-07-27T11:56:29Z)
• Dual-Branch Cross-Projection Debiasing through Diffusion-based Disentanglement [66.67463557274358]
  Foundation models trained on biased datasets often rely on spurious correlations between target labels and non-causal attributes.<n>We introduce Confidence-guided Concept Mining (CBCM) to identify reliable spurious attributes without attribute annotations.<n>We propose Dual-branch Cross-projection Debiasing (DCD), a prompt-tuning framework that separates target and spurious representations into two branches.
  arXiv  Detail & Related papers  (2026-06-23T05:28:47Z)
• CoT-Seg: Rethinking Segmentation with Chain-of-Thought Reasoning and Self-Correction [50.67483317563736]
  This paper aims to explore a system that can think step-by-step, look up information if needed, generate results, self-evaluate its own results, and refine the results.<n>We introduce CoT-Seg, a training-free framework that rethinks reasoning segmentation by combining chain-of-thought reasoning with self-correction.
  arXiv  Detail & Related papers  (2026-01-24T11:41:54Z)
• Codebook-Injected Dialogue Segmentation for Multi-Utterance Constructs Annotation: LLM-Assisted and Gold-Label-Free Evaluation [0.17240671897505613]
  Dialogue Act (DA) annotation treats communicative or pedagogical intent as localized to individual utterances or turns.<n>We propose codebook-injected segmentation, which conditions boundary decisions on downstream annotation criteria.<n>We find DA-awareness produces segments that are internally more consistent than text-only baselines.
  arXiv  Detail & Related papers  (2026-01-17T14:17:13Z)
• SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphs [28.59157823781425]
  SEAL is a novel two-stage semantic parsing framework grounded in self-evolving agentic learning.<n> SEAL achieves state-of-the-art performance, especially in multi-hop reasoning, comparison, and aggregation tasks.<n>The results validate notable gains in both structural accuracy and computational efficiency.
  arXiv  Detail & Related papers  (2025-12-04T14:52:30Z)
• DEPTH: Hallucination-Free Relation Extraction via Dependency-Aware Sentence Simplification and Two-tiered Hierarchical Refinement [22.164114662885652]
  DEPTH is a framework that integrates Dependency-aware sEntence simPlification and Two-tiered Hierarchical refinement into the relation extraction pipeline.<n>We show that DEPTH reduces the average hallucination rate to 7.0% while achieving a 17.2% improvement in average F1 score over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-08-20T03:35:24Z)
• Knowledge Graph Completion with Relation-Aware Anchor Enhancement [50.50944396454757]
  We propose a relation-aware anchor enhanced knowledge graph completion method (RAA-KGC)<n>We first generate anchor entities within the relation-aware neighborhood of the head entity.<n>Then, by pulling the query embedding towards the neighborhoods of the anchors, it is tuned to be more discriminative for target entity matching.
  arXiv  Detail & Related papers  (2025-04-08T15:22:08Z)
• Unsupervised Robust Cross-Lingual Entity Alignment via Neighbor Triple Matching with Entity and Relation Texts [17.477542644785483]
  Cross-lingual entity alignment (EA) enables the integration of multiple knowledge graphs (KGs) across different languages.<n>EA pipeline that jointly performs entity-level and Relation-level Alignment by neighbor triple matching strategy.
  arXiv  Detail & Related papers  (2024-07-22T12:25:48Z)
• Bring Your Own Data! Self-Supervised Evaluation for Large Language Models [52.15056231665816]
  We propose a framework for self-supervised evaluation of Large Language Models (LLMs) We demonstrate self-supervised evaluation strategies for measuring closed-book knowledge, toxicity, and long-range context dependence. We find strong correlations between self-supervised and human-supervised evaluations.
  arXiv  Detail & Related papers  (2023-06-23T17:59:09Z)
• Enriching Relation Extraction with OpenIE [70.52564277675056]
  Relation extraction (RE) is a sub-discipline of information extraction (IE) In this work, we explore how recent approaches for open information extraction (OpenIE) may help to improve the task of RE. Our experiments over two annotated corpora, KnowledgeNet and FewRel, demonstrate the improved accuracy of our enriched models.
  arXiv  Detail & Related papers  (2022-12-19T11:26:23Z)
• R$^2$-Net: Relation of Relation Learning Network for Sentence Semantic Matching [58.72111690643359]
  We propose a Relation of Relation Learning Network (R2-Net) for sentence semantic matching. We first employ BERT to encode the input sentences from a global perspective. Then a CNN-based encoder is designed to capture keywords and phrase information from a local perspective. To fully leverage labels for better relation information extraction, we introduce a self-supervised relation of relation classification task.
  arXiv  Detail & Related papers  (2020-12-16T13:11:30Z)

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.