No article text was recorded for this version.
cross-architecture generalizability
Version 1 of 124 papers24 conceptsfrozen 2026-10-04
Papers in this version
- Blog: A matter of framing: The impact of linguistic formalism on probing results
- Blog: Analyzing Phonetic and Graphemic Representations in End-to-End Automatic Speech Recognition
- Blog: Examining Cross-lingual Contextual Embeddings with Orthogonal Structural Probes
- Blog: How do Large Language Models Handle Multilingualism?
- Blog: Probing via Prompting
- Blog: How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study
- Blog: Improving a Strong Neural Parser with Conjunction-Specific Features
- Blog: Probing LLMs for Joint Encoding of Linguistic Categories
- Blog: Improving Arabic Dependency Parsing with Form-based and Functional Morphological Features
- Blog: Interpreting Language Models Through Knowledge Graph Extraction
- Blog: On the Relationship between Sentence Analogy Identification and Sentence Structure Encoding in Large Language Models
- Blog: When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes
- Blog: Languages You Know Influence Those You Learn: Impact of Language Characteristics on Multi-Lingual Text-to-Text Transfer
- Blog: Morphological Features of the Irish Universal Dependencies Treebank
- Blog: Spectral Probing
- Blog: How Programming Concepts and Neurons Are Shared in Code Language Models
- Blog: Latent Topology Induction for Understanding Contextualized Representations
- Blog: Converging to a Lingua Franca: Evolution of Linguistic Regions and Semantics Alignment in Multilingual Large Language Models
- Blog: Unsupervised and Few-shot Parsing from Pretrained Language Models
- Blog: BERT Rediscovers the Classical NLP Pipeline
- Blog: Beyond Words: Integrating Theory of Mind into Conversational Agents for Human-Like Belief, Desire, and Intention Alignment
- Blog: Predicting Fine-Tuning Performance with Probing
- Blog: Code-Mixed Probes Show How Pre-Trained Models Generalise on Code-Switched Text
- Blog: Exploring the Role of BERT Token Representations to Explain Sentence Probing Results
History & citation
Current · Permanent link
- This direction split from Mechanistic Localization of Algorithmic Circuits in Language Models (50% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_cross_architecture_generalizability_327f1724,
title = {cross-architecture generalizability},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-architecture-generalizability/rdr_327f17242d53457293621a6074410ad1},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_cross_architecture_generalizability_327f1724_v1,
title = {cross-architecture generalizability},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-architecture-generalizability/rdr_327f17242d53457293621a6074410ad1/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}