paper-with-me

Papers

SemBench: A Universal Semantic Framework for LLM Evaluation

2026-03-12 · Mikel Zubillaga, Naiara Perez, Oscar Sainz, German Rigau arxiv

Recent progress in Natural Language Processing (NLP) has been driven by the emergence of Large Language Models (LLMs), which exhibit remarkable generative and reasoning capabilities. However, despite their success, evaluating the true semantic understanding of these models remains a persistent challenge. Traditional benchmarks such as Word-in-Context (WiC) effectively probe this capability, but their creation is resource-intensive and often limited to high-resource languages. In this paper, we introduce SemBench, a framework for automatically generating synthetic benchmarks that assess the semantic competence of LLMs using only dictionary sense definitions and a sentence encoder. This approach eliminates the need for curated example sentences, making it both scalable and language-independent. We evaluate SemBench in three languages (English, Spanish, and Basque) spanning different levels of linguistic resources, and across a wide range of LLMs. Our results show that rankings derived from SemBench strongly correlate with those obtained from standard WiC datasets. Furthermore, our analysis demonstrates that only a small number of examples is required to achieve stable and meaningful rankings. Overall, SemBench provides a lightweight, adaptable, and data-efficient framework for cross-lingual evaluation of semantic understanding in LLMs.

📄 PDF Abstract BibTeX arXiv:2603.11687

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

AssemLM: A Spatial Reasoning Multimodal Large Language Model for Robotic Assembly

2026-04-10 · Zhi Jing, Jinbin Qiao, Ouyang Lu, Jicong Ao 외 arxiv

Spatial reasoning is a fundamental capability for embodied intelligence, especially for fine-grained manipulation tasks such as robotic assembly. Recent methods based on vision-language models (VLMs) largely rely on coar…

Spatial ReasoningPoint Clouds

SemBench: A Benchmark for Semantic Query Processing Engines

2025-11-03 · Jiale Lao, Andreas Zimmerer, Olga Ovcharenko, Tianji Cong 외 arxiv

We present a benchmark targeting a novel class of systems: semantic query processing engines. Those systems rely inherently on generative and reasoning capabilities of state-of-the-art large language models (LLMs). They …

Towards Universal Semantics With Large Language Models

2025-05-17 · Raymond Baartmans, Matthew Raffel, Rahul Vikram, Aiden Deringer 외

The Natural Semantic Metalanguage (NSM) is a linguistic theory based on a universal set of semantic primes: simple, primitive word-meanings that have been shown to exist in most, if not all, languages of the world. Accor…

SAGE: A Unified Algebra and Self-Adaptive Execution for AI Functions in SQL

2026-08-21 · Xiangqi Wang, Nhan H. Pham, Oktie Hassanzadeh, Dharmashankar Subramanian 외 arxiv

SQL systems increasingly expose AI functions for tasks such as classification, extraction, filtering, ranking, retrieval, joining, and summarization. Despite their diverse APIs, these functions play only three relational…

Universal Refusal Circuits Across LLMs: Cross-Model Transfer via Trajectory Replay and Concept-Basis Reconstruction

2026-01-22 · Tony Cristofano arxiv

Refusal behavior in aligned LLMs is often viewed as model-specific, yet we hypothesize it stems from a universal, low-dimensional semantic circuit shared across models. To test this, we introduce Trajectory Replay via Co…