Probing Language Models
11 papers with code • 1 benchmarks • 3 datasets
BioLAMA
KAMEL
BEAR-probe
Most implemented papers
Universal and Independent: Multilingual Probing Framework for Exhaustive Model Interpretation and Evaluation
airi-institute/probing_framework
•
•
Thus we propose a toolkit to systematize the multilingual flaws in multilingual models, providing a reproducible experimental setup for 104 languages and 80 morphosyntactic features.
Quantifying Gender Bias Towards Politicians in Cross-Lingual Language Models
Recent research has demonstrated that large pre-trained language models reflect societal biases expressed in natural language.
Probing Toxic Content in Large Pre-Trained Language Models
HKUST-KnowComp/Probing_toxicity_in_PTLMs
•
•
ACL 2021
Large pre-trained language models (PTLMs) have been shown to carry biases towards different social groups which leads to the reproduction of stereotypical and toxic content by major NLP systems.
Probing Language Models for Understanding of Temporal Expressions
We present three Natural Language Inference (NLI) challenge sets that can evaluate NLI models on their understanding of temporal expressions.
The neural architecture of language: Integrative modeling converges on predictive processing
mschrimpf/neural-nlp
•
•
Proceedings of the National Academy of Sciences 2021
The neuroscience of perception has recently been revolutionized with an integrative modeling approach in which computation, brain function, and behavior are linked across many datasets and many computational models.
Discontinuous Constituency and BERT: A Case Study of Dutch
gijswijnholds/discontinuous-probing
•
•
Findings (ACL) 2022
In this paper, we set out to quantify the syntactic capacity of BERT in the evaluation regime of non-context free patterns, as occurring in Dutch.
KAMEL : Knowledge Analysis with Multitoken Entities in Language Models
JanKalo/KAMEL
•
•
Automated Knowledge Base Construction 2022
Instead of performing the evaluation on masked language models, we present results for a variety of recent causal LMs in a few-shot setting.
Probing Representations for Document-level Event Extraction
This work is the first to apply the probing paradigm to representations learned for document-level information extraction (IE).
Unveiling LLMs: The Evolution of Latent Representations in a Dynamic Knowledge Graph
We propose an end-to-end framework to decode factual knowledge embedded in token representations from a vector space to a set of ground predicates, showing its layer-wise evolution using a dynamic knowledge graph.
Probing Language Models for Pre-training Data Detection
Large Language Models (LLMs) have shown their impressive capabilities, while also raising concerns about the data contamination problems due to privacy issues and leakage of benchmark datasets in the pre-training phase.
