Differences in Typological Alignment in Language Models' Treatment of Differential Argument Marking

Research Summary

Contribution Summary

• Recent work has shown that language models (LMs) trained on synthetic corpora can exhibit typological preferences that resemble cross-linguistic regularities in human languages, particularly for syntactic phenomena such as word order.
• In this paper, we extend this paradigm to differential argument marking (DAM), a semantic licensing system in which morphological marking depends on semantic prominence.
• Using a controlled synthetic learning method, we train GPT-2 models on 18 corpora implementing distinct DAM systems and evaluate their generalization using minimal pairs.

Why It Matters For Eval

• Recent work has shown that language models (LMs) trained on synthetic corpora can exhibit typological preferences that resemble cross-linguistic regularities in human languages, particularly for syntactic phenomena such as word order.
• Models reliably exhibit human-like preferences for natural markedness direction, favoring systems in which overt marking targets semantically atypical arguments.

Related Papers

• LogiPart: Local Large Language Models for Data Exploration at Scale with Logical Partitioning Embedding Neighbor
• Counterfactual Fairness Evaluation of LLM-Based Contact Center Agent Quality Assurance System Embedding Neighbor
• Eigenmood Space: Uncertainty-Aware Spectral Graph Analysis of Psychological Patterns in Classical Persian Poetry Embedding Neighbor
• Continuous Telemonitoring of Heart Failure using Personalised Speech Dynamics Embedding Neighbor
• Revisiting Northrop Frye's Four Myths Theory with Large Language Models Embedding Neighbor
• On the Semantic and Syntactic Information Encoded in Proto-Tokens for One-Step Text Reconstruction Embedding Neighbor
• HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam Embedding Neighbor
• AgenticRAGTracer: A Hop-Aware Benchmark for Diagnosing Multi-Step Retrieval Reasoning in Agentic RAG Embedding Neighbor
• CUICurate: A GraphRAG-based Framework for Automated Clinical Concept Curation for NLP applications Embedding Neighbor
• Designing and Evaluating Chain-of-Hints for Scientific Question Answering Tag Overlap
• The ASIR Courage Model: A Phase-Dynamic Framework for Truth Transitions in Human and AI Systems Tag Overlap
• BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning Tag Overlap