Disentangling Statistical Preemption from Entrenchment in Language Models' Avoidance of Overgeneralization

arXiv:2609.01794 · cs.CL · Submitted 2026-09-01 · Read on arXiv

cs.CL

Submitted: 2026-09-01

Updated: 2026-09-01

Code: https://github.com/Yixuan-Wang/verb-overgen

Terminology

• Periphrastic Causative — 58× in this paper
• Generalization — 19× in this paper · explained in 13 episodes
• Transformer — 8× in this paper · explained in 2 episodes
• Alternation — 4× in this paper · explained in 1 episode
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Tokenization — 2× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Byte-Pair Encoding — 1× in this paper
• Core — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• BabyLM Turns 4 and Goes Multilingual: Call for Papers for the 2026 BabyLM Workshop
• A systematic framework for generating novel experimental hypotheses from language models
• CAIT: A Syntactic Parsing Toolkit for Child-Adult InTeractions
• The Mechanistic Emergence of Symbol Grounding in Language Models
• A Unified Assessment of the Poverty of the Stimulus Argument for Neural Language Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering