Compositionality

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 23

All topics

Compound interpretation is based on analogy
Oct 1, 2026Tian Shen, Harald BaayenCompositionality Analogy
School of Foreign Languages, Northwest University, Xi’an, China · Department of Quantitative Linguistics, University of Tübingen, Tübingen, Germany
Do Audio Representations Compose Additively?
Sep 23, 2026Chenhao Xue, Zhijin Guo, Joyraj Chakraborty +2Audio Understanding Speech-To-Text Alignment
Department of Engineering Science, University of Oxford, Oxford, UK · University of Essex, Colchester, UK
Hierarchical Compositionality for An Assistive AI Agent
Aug 11, 2026Tianyi Fu, Mohan SridharanArtificial Intelligence Agents Compositionality
University of Edinburgh, Edinburgh, United Kingdom
Geo-Spatial Concept Probing of Large Language Models: Abstraction, Compositionality, and Grounding
Aug 7, 2026Karim Radouane, Jose G Moreno, Lynda TamineLegal Natural Language Processing Benchmarks Compositionality
University of Toulouse, IRIT Toulouse, France
Evolving language compositionality in a frequency-structured meaning space
Jul 31, 2026Fabio De Ponte, Eloise Gaines-White, Conor Houghton +1Language Acquisition Compositionality
Université de Namur and Vrije Universiteit Brussel, Belgium · University of Bristol, UK
From Dependency to Compositionality: A Neurosymbolic Lifting of LLM Outputs via Combinatory Categorial Grammar
Jul 21, 2026Remo PareschiContext-Free Grammars Compositionality
STAKE Lab, University of Molise, Campobasso, Italy
Losing My Composure: Predicting Compositionality Over Time
Jul 13, 2026Chris Jenkins, Emma Raimundo Schulz, Filip Miletić +1Compositionality
University of Stuttgart
Attribute Retrieving for Open-Vocabulary Endoscopic Compositional Referring Segmentation
Jul 9, 2026Shun Liu, Nan Xi, Yang Liu +3Colonoscopy Image-Text Pairs
Virginia Commonwealth University · King’s College London · University at Buffalo +1
Compositionality and the lexicon in evolutionary semantics
Jun 25, 2026Fausto CarcassiCompositionality Syntactic Structure
Institute for Logic, Language, and Computation, University of Amsterdam, Amsterdam, Netherlands
Compositionality Emerges in a Narrow Depth-Connectivity Regime: Architecture Constraints and Solution Manifolds
Jun 18, 2026Dat H. Do, Rushi Shah, Duc V. Le +1Compositionality Deep Network
National University of Singapore1 · University of Twente2
Compositional Reasoning Depth Predicts Clinical AI Failure: Empirical Evidence Consistent with Transformer Compositionality Limits in Electronic Health Record Question Answering
Jun 15, 2026Sanjay BasuClinical Reasoning Training Compositionality
Department of Medicine, University of California San Francisco, San Francisco, CA · Waymark, San Francisco, CA
Emergent retokenization symmetry in large language models: phenomenology and applications
Jun 14, 2026Kanishk Jain, Matthew Day, Tankut CanCompositionality Redundancy
Department of Physics, Emory University, Atlanta, GA 30322
Cross-Modal Masked Compositional Concept Modeling for Enhancing Visio-Linguistic Compositionality
Jun 11, 2026Wei Li, Zhen Huang, Xinmei TianImage-Text Pairs Cross-Modal
MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China · Independent Researcher
Principles of Concept Representation in Sentence Encoders
Jun 5, 2026Isabelle Mohr, John Dujany, Jonathan Souquet +1Sentence Encoders Semantic Representations
Idiap Research Institute · Merck KGaA
Compositional Boundaries for Density Fusion
Jun 4, 2026Ratan Bahadur Thapa, Ali Darijani, Jürgen Beyerer +1Global-Local Fusion Framework Bregman Divergences
Comonadic Morphophonology: A Compositional Framework for Context-Dependent Morphological Rules in Finnish
May 27, 2026Yongseok JangMorphology Compositionality
Independent Researcher
No Safe Dose: How Training Data Drives Unsafe Image Generation
May 27, 2026Felix Friedrich, Lukas Helff, Niharika Hegde +2Text-To-Image Large Language Model Safety
1Black Forest Labs · 2TU Darmstadt & hessian.AI · 3DFKI +1
Towards a compositional semantics for quantitative confidence assessment in assurance arguments
May 21, 2026Benjamin Herd, Jessica Kelly, Jan Sabsch +1Confidence Calibration Confidence Estimation
Fraunhofer IKS · Munich, Germany · Luxoft GmbH +2
Hypergraph Pattern Machine: Compositional Tokenization for Higher-Order Interactions
May 15, 2026Kyrie Zhao, Zehong Wang, Tianyi Ma +5Hypergraphs Drug-Drug Interactions
University of Notre Dame · Stanford University · Yale University +2
From Mechanistic to Compositional Interpretability
May 9, 2026Ward Gauderis, Thomas Dooms, Steven T. Homer +2Mechanistic Interpretability Interpretability
Vrije Universiteit Brussel, Brussels, Belgium · Independent · UK AI Security Institute, London, United Kingdom.
Conceptors for Semantic Steering
May 6, 2026Ilias Triantafyllopoulos, Young-Min Cho, Ren Tao +6Linear Activation Steering Steering
1New York University · University of Pennsylvania
Investigating More Explainable and Partition-Free Compositionality Estimation for LLMs: A Rule-Generation Perspective
Apr 30, 2026Ziyao Xu, Cong Wang, Houfeng WangCompositional Generalization Compositionality
National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University · OPPO AI Center
Grounding vs. Compositionality: On the Non-Complementarity of Reasoning in Neuro-Symbolic Systems
Apr 29, 2026Mahnoor Shahid, Hannes RotheNeuro-Symbolic Framework Compositional Generalization
Universität Duisburg Essen, Germany

Oct 1, 2026, cs.CLJ/K move · Enter open · S save

Compound interpretation is based on analogy

Tian Shen, Harald Baayen

School of Foreign Languages, Northwest University, Xi’an, China · Department of Quantitative Linguistics, University of Tübingen, Tübingen, Germany

Compositionality Analogy Semantic Relationships Interpretation

Open paper AskPDF arXiv

How compound meanings are best predicted from constituent meanings remains a central question in computational models of lexical semantics. Comparing different computational models provides a way to evaluate alternative accounts of how semantic information is combined during compound comprehension. We propose a new model, the Compound Analogy Model (CAM), that predicts a compound's embedding by adding its constituent embeddings together with the average shift vectors of the two constituents' compound families. The resulting model is parameter-free and exploits local analogical structure in the semantic space. We evaluated CAM against the CAOSS model on Mandarin Chinese compounds. CAM consistently achieved higher prediction accuracy than CAOSS on both training and held-out data, with the exception of three-character compounds, for which analogical generalization is constrained by both small constituent families and a pronounced imbalance in family size between the two constituents. The advantage of CAM remained when evaluation was based on frequency-defined train-test splits that better approximate generalization from familiar to novel compounds. To assess the cognitive plausibility of the two models, we further examined whether model-derived semantic measures predict visual lexical decision latencies for two-character compounds. Predictors derived from CAM provided improved prediction for response latencies compared to predictors derived from the CAOSS model. These findings indicate that compound meaning is better characterized as local analogical generalization than as the application of a learned global linear transformation, and demonstrate that analogical semantic structure provides a cognitively plausible basis for compound comprehension.

Momentum

Related topics

Latest papers 23