Contextual trajectory and incremental contextual displacement: Towards using LLMs to understand dynamic, utterance-specific meaning construction
cs.CL, cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Terminology
Sources
- Dissociating language and thought in large language models
- LLMs are not stochastic parrots: Evidence for meaning-mediated abstraction from conlang-like tasks
- Efficient Estimation of Word Representations in Vector Space
- Improving the Coverage and the Generalization Ability of Neural Word Sense Disambiguation through Hypernymy and Hyponymy Relationships
- Does BERT Make Any Sense? Interpretable Word Sense Disambiguation with Contextualized Embeddings
- Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic State
- Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space
- Tokens, the oft-overlooked appetizer: Large language models, the distributional hypothesis, and meaning
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
- DeBERTa: Decoding-enhanced BERT with Disentangled Attention
- Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve
- The Last Fingerprint: How Markdown Training Shapes LLM Prose
- Does Prompt Formatting Have Any Impact on LLM Performance?
- Revisiting Real-Time Digging-In Effects: No Evidence from NP/Z Garden-Paths
- UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
- Lexinvariant Language Models
- Practical and Ready-to-Use Methodology to Assess the re-identification Risk in Anonymized Datasets
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