mlsanityData to 7 Oct 2026

Language-Specific versus Cross-Lingual Knowledge Graphs for Implicit Aspect Identification in Arabic: A Comparative Study of Reasoning and Adaptation Strategies

arXiv 2607.20056 ↗First posted 22 Jul 2026cs.CL cs.AIcited by 0

On the map: LLM reasoning → Audio-language model reasoning

Abstract (arXiv)

Aspect-based sentiment analysis (ABSA) in Arabic must recover both explicitly stated aspects and implicit aspects that are never named in the text. Implicit identification typically relies on an auxiliary knowledge source (e.g., a knowledge graph (KG)) linking opinion cues to aspect categories, but for a lower-resource language the practitioner faces a design choice: reuse a mature English KG through multilingual embeddings, or build a smaller native Arabic KG. This paper reports a controlled comparison of the two strategies within a single hybrid pipeline, evaluated on three Arabic benchmarks (M-ABSA, SemEval-2016 Arabic, and HAAD). We further compare two adaptation strategies for the generative extractor that feeds the KG -- zero-shot prompting versus task-specific fine-tuning of an 8B-parameter large language model (LLM). The native Arabic KG (Strategy 2) outperforms the cross-lingual English KG (Strategy 1) by +0.199 micro-F1 on M-ABSA and +0.251 on SemEval-2016, gaining on both precision and recall. Task-specific fine-tuning raises explicit-extraction micro-F1 from <= 0.13 (zero-shot) to 0.66-0.76 on M-ABSA and SemEval-2016 (0.45 on the smaller HAAD), confirming that task adaptation, rather than model scale, is decisive in a morphologically rich language.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning. Builds on 3 of its 5 references that are in the map. First posted on arXiv 22 Jul 2026.

Builds on

3 of 5 references.

References · 3

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 591

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Evaluating Zero-Shot Multilingual Aspect-Based Sentiment Analysis with Large Language Models
  2. 2025From Annotation to Adaptation: Metrics, Synthetic Data, and Aspect Extraction for Aspect-Based Sentiment Analysis with Large Language Models
  3. 2026Large-Scale Aspect-Based Sentiment Analysis with Reasoning-Infused LLMs
  4. 2023On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training
  5. 2025UI-Level Evaluation of ALLaM 34B: Measuring an Arabic-Centric LLM via HUMAIN Chat
  6. 2025Multi-Domain ABSA Conversation Dataset Generation via LLMs for Real-World Evaluation and Model Comparison
  7. 2025Exploring Zero-Shot ACSA with Unified Meaning Representation in Chain-of-Thought Prompting
  8. 2024Enhancing Long-Range Dependency with State Space Model and Kolmogorov-Arnold Networks for Aspect-Based Sentiment Analysis