inverse scaling

Surprisal and Metaphor Novelty Judgments: Moderate Correlations and Divergent Scaling Effects Revealed by Corpus-Based and Synthetic Datasets EACL 2026 Surprisal from Larger Transformer-based Language Models Predicts fMRI Data More Poorly EACL 2026 How Well Can Reasoning Models Identify and Recover from Unhelpful Thoughts? EMNLP 2025 Pitfalls of Scale: Investigating the Inverse Task of Redefinition in Large Language Models ACL 2025 The Inverse Scaling Effect of Pre-Trained Language Model Surprisal Is Not Due to Data Leakage ACL 2025 FRoG: Evaluating Fuzzy Reasoning of Generalized Quantifiers in LLMs EMNLP 2024 Scaling Behavior of Machine Translation with Large Language Models under Prompt Injection Attacks EACL 2024 Understanding Inverse Scaling and Emergence in Multitask Representation Learning AISTATS 2024 Beyond Positive Scaling: How Negation Impacts Scaling Trends of Language Models ACL 2023 Discovering Language Model Behaviors with Model-Written Evaluations ACL 2023 Emergent Inabilities? Inverse Scaling Over the Course of Pretraining EMNLP 2023 Inverse Scaling Can Become U-Shaped EMNLP 2023 Probing Quantifier Comprehension in Large Language Models: Another Example of Inverse Scaling EMNLP 2023 Rarely a problem? Language models exhibit inverse scaling in their predictions following few-type quantifiers ACL 2023 The Larger they are, the Harder they Fail: Language Models do not Recognize Identifier Swaps in Python ACL 2023