No article text was recorded for this version.
structural perturbation analysis
Version 2 of 291 papers96 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Does Character-level Information Always Improve DRS-based Semantic Parsing?
- Blog: Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study
- Blog: Analyzing Compositionality-Sensitivity of NLI Models
- Blog: Construction Identification and Disambiguation Using BERT: A Case Study of NPN
- Blog: ShufText: A Simple Black Box Approach to Evaluate the Fragility of Text Classification Models
- Blog: Schrödinger's Tree - On Syntax and Neural Language Models
- Blog: Beyond Surface Structure: A Causal Assessment of LLMs' Comprehension ability
- Blog: Syntactic Perturbations Reveal Representational Correlates of Hierarchical Phrase Structure in Pretrained Language Models
- Blog: Word Order's Impacts: Insights from Reordering and Generation Analysis
- Blog: Oolong: Investigating What Makes Transfer Learning Hard with Controlled Studies
- Blog: Sometimes We Want Ungrammatical Translations
- Blog: What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models
- Blog: When classifying grammatical role, BERT doesn't care about word order... except when it matters
- Blog: Robustness of Learning from Task Instructions
- Blog: When a sentence does not introduce a discourse entity, Transformer-based models still sometimes refer to it
- Blog: Mission: Impossible Language Models
- Blog: NLI Data Sanity Check: Assessing the Effect of Data Corruption on Model Performance
- Blog: Unveiling LLMs' Metaphorical Understanding: Exploring Conceptual Irrelevance, Context Leveraging and Syntactic Influence
- Blog: A Morphology-Based Investigation of Positional Encodings
- Blog: Re-Evaluating ADEM: A Deeper Look at Scoring Dialogue Responses
- Blog: DeltaScore: Fine-Grained Story Evaluation with Perturbations
- Blog: How much should you ask? On the question structure in QA systems
- Blog: MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization
- Blog: What do Models Learn from Question Answering Datasets?
- Blog: A Cross-linguistic Analysis of the Effects of Character-level Information in Neural Models
- Blog: NoLiMa: Long-Context Evaluation Beyond Literal Matching
- Blog: Evaluating Morphological Compositional Generalization in Large Language Models
- Blog: What Does BERT Learn about the Structure of Language?
- Blog: ShufText: A Simple Black Box Approach to Evaluate the Fragility of Text Classification Models
- Blog: Monoculture or Multiplicity: Which Is It?
- Blog: Cross-linguistic Comparison of Linguistic Feature Encoding in BERT Models for Typologically Different Languages
- Blog: ANALOGICAL - A Novel Benchmark for Long Text Analogy Evaluation in Large Language Models
- Blog: An Empirical study to understand the Compositional Prowess of Neural Dialog Models
- Blog: ICSVR: Investigating Compositional and Syntactic Understanding in Video Retrieval Models
- Blog: BERT might be Overkill: A Tiny but Effective Biomedical Entity Linker based on Residual Convolutional Neural Networks
- Blog: How well do NLI models capture verb veridicality?
- Blog: Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality
- Blog: D&R: Recovery-based AI-Generated Text Detection via a Single Black-box LLM Call
- Blog: The Locality and Symmetry of Positional Encodings
- Blog: Probing sentence embeddings for structure-dependent tense
- Blog: Numerical reasoning in machine reading comprehension tasks: are we there yet?
- Blog: The Rhythm of Lexical Stress in Prose
- Blog: A fine-grained comparison of pragmatic language understanding in humans and language models
- Blog: Do Long-Range Language Models Actually Use Long-Range Context?
- Blog: Trawling for Trolling: A Dataset
- Blog: Are Prompt-based Models Clueless?
- Blog: Analyzing Compositionality-Sensitivity of NLI Models
- Blog: UnNatural Language Inference
- Blog: Does Character-level Information Always Improve DRS-based Semantic Parsing?
- Blog: How Does BERT Rerank Passages? An Attribution Analysis with Information Bottlenecks
- Blog: What do Large Language Models Learn beyond Language?
- Blog: Cross-Lingual Ability of Multilingual BERT: An Empirical Study
- Blog: Shortcut Learning of Large Language Models in Natural Language Understanding
- Blog: An Examination of the Robustness of Reference-Free Image Captioning Evaluation Metrics
- Blog: Visual Referring Expression Recognition: What Do Systems Actually Learn?
- Blog: Towards preserving word order importance through Forced Invalidation
- Blog: BERT might be Overkill: A Tiny but Effective Biomedical Entity Linker based on Residual Convolutional Neural Networks
- Blog: An Empirical Study on the Language Modal in Visual Question Answering
- Blog: Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little
- Blog: When classifying grammatical role, BERT doesn't care about word order... except when it matters
Showing 60 of 91 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_structural_perturbation_analysis_ddea5846,
title = {structural perturbation analysis},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/structural-perturbation-analysis/rdr_ddea5846bb5a442383e949d44b1b0897},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_structural_perturbation_analysis_ddea5846_v2,
title = {structural perturbation analysis},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/structural-perturbation-analysis/rdr_ddea5846bb5a442383e949d44b1b0897/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}