conftrace_
← Core AI
Artificial Intelligence › Core AI ›

Interpretability

7,318 papers

Papers per year

Papers

A Legal Approach to Hate Speech – Operationalizing the EU’s Legal Framework against the Expression of Hatred as an NLP Task EMNLP 2022
The Legal Argument Reasoning Task in Civil Procedure EMNLP 2022
Legal and Political Stance Detection of SCOTUS Language EMNLP 2022
Critical Perspectives: A Benchmark Revealing Pitfalls in PerspectiveAPI EMNLP 2022
A Robust Bias Mitigation Procedure Based on the Stereotype Content Model EMNLP 2022
Who is GPT-3? An exploration of personality, values and demographics EMNLP 2022
(Psycho-)Linguistic Features Meet Transformer Models for Improved Explainable and Controllable Text Simplification EMNLP 2022
Assessing the Linguistic Knowledge in Arabic Pre-trained Language Models Using Minimal Pairs EMNLP 2022
Results of WMT22 Metrics Shared Task: Stop Using BLEU – Neural Metrics Are Better and More Robust EMNLP 2022
Analyzing the Use of Influence Functions for Instance-Specific Data Filtering in Neural Machine Translation EMNLP 2022
CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task EMNLP 2022
Meaningfully debugging model mistakes using conceptual counterfactual explanations ICML 2022
XAI for Transformers: Better Explanations through Conservative Propagation ICML 2022
A query-optimal algorithm for finding counterfactuals ICML 2022
UNIREX: A Unified Learning Framework for Language Model Rationale Extraction ICML 2022
Label-Free Explainability for Unsupervised Models ICML 2022
Self-conditioning Pre-Trained Language Models ICML 2022
Deep symbolic regression for recurrence prediction ICML 2022
Framework for Evaluating Faithfulness of Local Explanations ICML 2022
Lazy Estimation of Variable Importance for Large Neural Networks ICML 2022
A Functional Information Perspective on Model Interpretation ICML 2022
Inducing Causal Structure for Interpretable Neural Networks ICML 2022
Neuro-Symbolic Hierarchical Rule Induction ICML 2022
Adversarially trained neural representations may already be as robust as corresponding biological neural representations ICML 2022
Neuron Dependency Graphs: A Causal Abstraction of Neural Networks ICML 2022