Semantic Alignment

Latest papers

15 papers1 paper in the last four weeks, down 75% on the four weeks before. 0.0% of all new papers.

Language Unalignability: Why Some Concepts Resist Cross-Cultural Benchmark Evaluation
Oct 6, 2026Shu-Kai Hsieh, Da-Chen LianCultural Knowledge in Language Models LLM Evaluation
National Taiwan University
SVG-Score: Human-Aligned Evaluation of Text-to-SVG Generation
Sep 3, 2026Marco Cipriano, Leonardo Zini, Alexandra Schild +5VLM Evaluation Human Preference Modeling
Hasso-Plattner Institute, Germany · University of Modena and Reggio Emilia, Italy
Preference Shapes Relevance: Cross-component Hierarchical Semantic Alignment for Personalized Generative Retrieval
Aug 31, 2026Gaoming Zhang, Angqing Jiang, Jianchun Song +4Generative Retrieval Semantic Alignment
University of Science and Technology of China · Meituan
Argument-Aware Semantic Alignment of Normative Texts: A Toulmin-Based Neuro-Symbolic Approach
Aug 30, 2026William SchroederSemantic Alignment Neuro-Symbolic Reasoning
Purdue University; CTO Cleantech Software · CTO Cleantech Software
ITL: Interpretable Document Alignment with Structured Reference Frameworks
Aug 27, 2026Raúl Giráldez, Dayrelis Mena, Jesús S. Aguilar--RuizSemantic Alignment Concept Alignment
School of Engineering Pablo de Olavide University ES-41013 Seville, Spain
Semantic Alignment of AI Models: Concept Collapse, Checkpoint Dynamics, and Cross-Lingual Transfer
Aug 3, 2026Tyler Ashoff, Jordan RoduMultilingual Language Model Evaluation Representation Geometry in Language Models
Department of Statistics, University of Virginia. · Department of Statistics, University of Virginia
Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs
Jul 7, 2026Zhenyu Liu, Xuanyu Zhang, Yunxin Li +10Semantic Alignment Speech Language Models
School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China · Center for Language, Intelligence and Machines, Shenzhen Loop Area Institute, Shenzhen, China · 4PCG, Tencent, Shenzhen, China +1
MATCHA: Matching Text via Contrastive Semantic Alignment
May 26, 2026Siran Li, Ece Sena Etoglu, Carsten Eickhoff +1LLM Evaluation Semantic Textual Similarity
University of Tübingen
SpecAlign: A Semantic Alignment Framework for SystemVerilog Assertion Generation
May 24, 2026Jaime Rafael Imperial, Hao ZhengFormal Hardware Verification SystemVerilog Assertion Generation
Bellini College of Cybersecurity, AI, and Computing University of South Florida Tampa, USA
MuTSE: A Human-in-the-Loop Multi-use Text Simplification Evaluator
Apr 10, 2026Rares-Alexandru Roscan, Gabriel Petre1, Adrian-Marius Dumitran +1Semantic Alignment Text Simplification
University of Bucharest, Faculty of Mathematics and Computer Science, Academiei 14, 010014, Bucharest, Romania · Cu Drag si Sport SRL, Bucharest, Romania · Softbinator Technologies, Bucharest, Romania +1
Learning Concepts, Not Tokens: Self-Supervised Semantic Alignment for Language Models
Mar 31, 2026Christine Zhang, Dan Jurafsky, Chen ShaniLanguage Modeling LLM Alignment
Stanford University
Representation Learning to Study Temporal Dynamics in Tutorial Scaffolding
Mar 25, 2026Conrad Borchers, Jiayi Zhang, Ashish GurungInstructional Scaffolding Semantic Alignment
Carnegie Mellon University · Worcester Polytechnic Institute
Semantic Alignment across Ancient Egyptian Language Stages via Normalization-Aware Multitask Learning
Mar 25, 2026He HuangSemantic Alignment Cross-Lingual Representation Alignment
Institut für Ägyptologie und Koptologie, Ludwig-Maximilians-Universität München, Katharina-von-Bora-Straße 10, 80333 München, Germany
Unifying Ontology Construction and Semantic Alignment for Deterministic Enterprise Reasoning at Scale
Mar 11, 2026Hongyin ZhuSemantic Alignment Ontology Learning
Yonyou AI Lab · Yonyou Network Technology Co., Ltd.
Structured Prompt Optimization for Few-Shot Text Classification via Semantic Alignment in Latent Space
Feb 27, 2026Jiasen Zheng, Zijun Zhou, Huajun Zhang +3Semantic Alignment Few-Shot Text Classification
Northwestern University, Evanston, USA · Independent Researcher, San Jose, USA · Syracuse University, Syracuse, USA +3

Oct 6, 2026J/K move · Enter open · S save

Language Unalignability: Why Some Concepts Resist Cross-Cultural Benchmark Evaluation

Shu-Kai Hsieh, Da-Chen Lian

National Taiwan University

Cultural Knowledge in Language Models LLM Evaluation Cross-Cultural Language Model Evaluation Multilingual Language Model Evaluation Cross-Lingual Representation Alignment Concept Alignment+1

Open paper AskPDF arXiv

Current evaluation of multilingual Large Language Models (LLMs) rests on an implicit Translation-Isomorphism Assumption (TIA): that semantic structures across languages are congruent and mutually mappable without loss of information. We argue that this assumption is not merely violated in practice, but ill-posed in principle for a typologically identifiable class of concepts, including pragmatic markers, honorifics, and diachronically stratified terms. We formalize this failure using a usage-cloud framework, representing concepts as point sets of contextualized embeddings. We define

α

-unalignability as the impossibility of any mapping that simultaneously preserves lexical faithfulness (centroid correspondence) and structural faithfulness (local neighborhood topology). We provide three layers of evidence. Behaviorally, we show that FLORES-200 translation failures are predicted by language family and resource class but not by script, and that LOBSTER reasoning scores vary by family. Mechanistically, we report a Representation-Intervention Gap (RIG) in a nine-model case study on Yami: the models' activations encode a regularity along which Yami groups with other low-resource and Austronesian languages, yet interventions on language-specific neurons show no demonstrated advantage over random masks: the regularity is visible but not usable by this intervention. Finally, we operationalize these findings into a multidimensional diagnostic profile: Cycle-Consistency, Pragmatic-Load Disagreement, Manifold-Curvature Mismatch, and RIG. We argue that collapsing cultural competence into a single scalar incentivizes "probabilistic flattening," and that recognizing the unalignable class is a precondition for AI that respects, rather than erases, cultural divergence. This suggests that multilingual alignment is not a single well-defined objective, but a set of mutually incompatible projections.