The proposed IRIS (Identity Representations from Internal States), a training-free framework that constructs for each entity an iris-like signature encoding its distinctive and stable identity characteristics, thereby forming a shared space in which each entity is encoded once and can be aligned across different KGs through direct similarity comparison.
Abstract
Entity alignment (EA) identifies entities across knowledge graphs (KGs) that refer to the same real-world object. Conventional EA methods mainly exploit explicit graph structures and textual fields, which often provide insufficient semantic understanding to recognize the same entity under heterogeneous descriptions and distinguish it from semantically similar entities. Although large language models (LLMs) offer deeper entity understanding, existing LLM-based EA methods largely use this capability for auxiliary generation or candidate-conditioned decisions. Consequently, such understanding is not distilled into a stable and directly comparable identity space, leaving alignment tied to specific KG pairs or candidate sets and requiring repeated processing as the matching context changes. To address these limitations, we propose IRIS (Identity Representations from Internal States), a training-free framework that constructs for each entity an iris-like signature encoding its distinctive and stable identity characteristics. IRIS derives these signatures by eliciting identity-oriented contextual representations from a frozen LLM, thereby forming a shared space in which each entity is encoded once and can be aligned across different KGs through direct similarity comparison, without pair-dependent representation construction or candidate-wise LLM inference. Across four established EA benchmarks and two frozen LLM backbones, the best IRIS variants achieve Hits@1 scores of 100.00, 99.38, 98.31, and 97.99 on D-Y-15K V2, DBP-WIKI, ICEWS-WIKI, and ICEWS-YAGO, respectively.
General-purpose text embedding models are designed to capture semantic similarity but are not optimised for distinguishing entity records that represent the same real-world business or person. This limitation affects applications such as entity resolution and duplicate record retrieval, where small textual differences may either preserve or change identity. This paper investigates whether domain-specific triplet fine-tuning can adapt pretrained embedding models for identity-sensitive retrieval. A synthetic dataset of business and person records was created with identity-preserving variations and challenging non-matching examples. Two widely used embedding models were evaluated before and after fine-tuning using a margin-based similarity evaluation. The results show substantial improvements in separating true matches from highly similar non-matches, demonstrating that domain-specific triplet training can effectively reshape general-purpose embedding spaces for entity retrieval. These findings suggest that targeted fine-tuning provides a practical approach for improving embedding models in data quality management and information retrieval applications.
Entity matching is a fundamental task in a wide range of retrieval and knowledge applications, aiming to identify whether two objects correspond to the same real-world entity across heterogeneous sources. Typical variants include entity resolution (ER), entity linking (EL), and entity alignment (EA). While recent unified matchers have made progress through multi-task training with comprehensive annotations, real-world pipelines often operate under scarce supervision, where labeled data is incomplete and fails to cover the full spectrum of matching scenarios. In this regime, supervised unified models degrade substantially, and deployable compact LLMs remain unreliable: lightweight fine-tuning and in-context learning yield inconsistent behavior and can even exhibit negative effects under scenario shifts. To fill in this gap, we propose øurs, a meta-rule induction and retrieval framework for unified entity matching under scarce supervision. Instead of relying on parametric adaptation, øurs converts limited supervision into explicit natural-language rules, abstracts them into reusable meta-rules via hierarchical clustering, and retrieves the most relevant meta-rules to guide the LLM's inference for each input instance. This design improves robustness by grounding decisions on explicit and reusable evidence, instead of relying solely on implicit adaptation or prompt demonstrations. Extensive experiments show that øurs achieves state-of-the-art performance on unified entity matching under scarce supervision.
Ziheng Zhang, Weixin Zeng, Jiuyang Tang et al.· Annual International ACM SIG...· 0 citations
The factors underlying performance differences across matcher architectures are clarified and motivate future research and benchmark designs that better disentangle architectural choices from model-level factors while explicitly evaluating distribution shift and cross-dataset transferability.
Zeyu Zhang, Xue Li, Iacer Calixto et al.· 0 citations
Explanation techniques such as local interpretable model-agnostic explanation (LIME) provide reasons behind decisions made by machine-learning models. These methods typically use a set of features and their values as inputs and identify those that significantly influence the final decision. However, machine-learning models for entity matching operate on two sets of tokens or records, each representing an entity, to determine whether they refer to the same real-world entity. Explanations for entity-matching decisions are more convincing when they highlight contributing pairs of tokens within the pair of records, rather than focusing on individual tokens alone. In this sense, existing explanation techniques are insufficient for entity matching. Therefore, we propose a new method, Pair INterpretation for Entity matching (PINE), which takes two records as input, and outputs correlated token pairs as an explanation for an entity-matching decision. Our extensive experiments on public datasets demonstrate that the extracted token pairs exhibit strong correlations and serve as interpretable evidence for matching records.
Hironori Mizuguchi, H. Kitagawa· The VLDB journal· 0 citations
Entity alignment across multi-source knowledge bases is frequently hindered by the problem of ’heterogeneous names but equivalent semantics,’ a challenge that becomes particularly acute in domains with specialized nomenclature and rare characters, such as cultural relics. To address this universal issue, this paper proposes a joint-embedding framework, MulF-ELMo-BERT, suitable for entity alignment in cultural relic knowledge graphs. This framework integrates multi-dimensional features such as entity names, attributes, summaries, and full-text texts, achieving comprehensive extraction of entity features from four levels: characters, words, sentences, and paragraphs. It effectively filters out weakly relevant entities and breaks through the limitations of semantic representation relying solely on a single feature. Given the dense presence of rare characters and specialized terms in cultural relic entity names, the ELMo context-aware word embedding model is introduced. It can dynamically adjust the vector representation of rare words based on their context, significantly enhancing semantic adaptability. Meanwhile, a Chinese BERT model with an integrated whole-word masking strategy is adopted to avoid local co-occurrence interference
Min Zhang, Luya Yang, Yaxian Gao et al.· INTERNATIONAL JOURNAL OF COM...· 0 citations
Extraction produces candidate entities and relationships; writing them into a graph is where identity is decided, and identity decisions are destructive in a way extraction errors are not. A wrong type can be corrected later, but two records merged under one identity cannot be separated once their properties have been combined, and the merge leaves no error behind. This paper describes the ingestion and ontology-tagging layer that turns a validated extraction stream into a knowledge graph of 537,157 entities and 2,198,567 relationships drawn from 98,795 government documents. We describe a record-identity ladder that decides sameness from identifier columns, name columns, display names and type-scoped position rather than from name similarity. The ladder governs de-duplication within parsed tables, while the graph write applies a coarser canonical-name key, so records sharing a canonical name merge automatically on exact equality. We argue rather than demonstrate that this is where the automation line belongs: no identity benchmark is reported, and the over-merges the key permits are undetectable by construction. That policy, under which entity resolution only ever flags candidates, followed an incident in which two surface forms of one name were merged, corrupting a correct record and deleting eight entities from an unrelated document. We then describe multi-class ontology tagging and an evidence asymmetry we did not anticipate: an entity name is an instance label rather than a type assertion, so matching name fragments against a class index invents classifications. Requiring anchored evidence cut role assignments on an enriched sample from 36 to 4, all confirmed correct. We quantify the graph's conformance debt, show secondary classifications compensating for a mis-parented primary class, and describe a curation queue grown to 48,403 pending proposals against 775 human decisions.
Vaibhav Dangaich, Kevin Lewis, Kundeshwar Pundalik· 0 citations