Entity · paper

Revisiting the Systematicity in Negation in the Era of In-Context Learning

paperactiverevisiting-the-systematicity-in-negation-in-the-era-of-in-context-learning-b8651811·1 events·first seen Jun 16, 2026

Aliases: Revisiting the Systematicity in Negation in the Era of In-Context Learning

More like this (12)

Multi-Task Bayesian In-Context Learning On the Limits of Prompt-Conditioned Language Models as General-Purpose Learners TILDE: TILt-based Distributional Erasure for Concept Unlearning Induction in Both Directions: A Mechanistic Analysis of In-Context Learning in Masked Diffusion Language Models When English Isn't the Best Teacher: Source Language Effects in Cross-Lingual In-Context Learning Fodor and Pylyshyn's Systematicity Challenge Still Stands Surprises in Proper Positive-Only Learning Natural Language Inference Logical Judgments Under Pressure: Diagnosing Syllogistic Stability with Learned Soft Prefixes in-context learning Explicit Fuzzy Logic in the Feed-Forward Layer: Self-Forgetting Quantifiers Discover Legible Grammatical-Licensing Detectors Reinforcement Learning Elicits Contextual Learning of Unseen Language Translation

Recent events (1)

3arXiv · cs.CL·Jun 16, 2026·source ↗

Revisiting LLM systematicity in negation understanding via in-context learning

A new arXiv preprint analyzes how well large language models handle negation from two angles: behavioral systematicity (whether models correctly recognize negation expressions and scope) and representational systematicity (whether function vectors can be reliably constructed from in-context examples). Results show LLMs partially succeed at negation cue recognition via in-context learning but struggle with scope recognition, with performance varying by output format. Function vectors can be composed for cue extraction but are harder to extract for scope recognition tasks.

Evaluation and Benchmarking Revisiting the Systematicity in Negation in the Era of In-Context Learning