conftrace_
← Core AI
Artificial Intelligence › Core AI ›

Interpretability

7,318 papers

Papers per year

Papers

Curriculum: A Broad-Coverage Benchmark for Linguistic Phenomena in Natural Language Understanding NAACL 2022
Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts NAACL 2022
Can Rationalization Improve Robustness? NAACL 2022
What Factors Should Paper-Reviewer Assignments Rely On? Community Perspectives on Issues and Ideals in Conference Peer-Review NAACL 2022
ExSum: From Local Explanations to Model Understanding NAACL 2022
When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes NAACL 2022
CONFIT: Toward Faithful Dialogue Summarization with Linguistically-Informed Contrastive Fine-tuning NAACL 2022
What do Toothbrushes do in the Kitchen? How Transformers Think our World is Structured NAACL 2022
Explaining Dialogue Evaluation Metrics using Adversarial Behavioral Analysis NAACL 2022
Probe-Less Probing of BERT’s Layer-Wise Linguistic Knowledge with Masked Word Prediction NAACL 2022
Contrastive Explanations of Text Classifiers as a Service NAACL 2022
Human-Centered Evaluation of Explanations NAACL 2022
AB/BA analysis: A framework for estimating keyword spotting recall improvement while maintaining audio privacy NAACL 2022
Developing a Production System for Purpose of Call Detection in Business Phone Conversations NAACL 2022
SemAttack: Natural Textual Attacks via Different Semantic Spaces NAACL 2022
Design Challenges for a Multi-Perspective Search Engine NAACL 2022
Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner NAACL 2022
Measuring and Improving Compositional Generalization in Text-to-SQL via Component Alignment NAACL 2022
MM-Claims: A Dataset for Multimodal Claim Detection in Social Media NAACL 2022
Probing the Role of Positional Information in Vision-Language Models NAACL 2022
Phrase-level Textual Adversarial Attack with Label Preservation NAACL 2022
FAtNet: Cost-Effective Approach Towards Mitigating the Linguistic Bias in Speaker Verification Systems NAACL 2022
Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models NAACL 2022
Minimally-Supervised Relation Induction from Pre-trained Language Model NAACL 2022
Exploring the Universal Vulnerability of Prompt-based Learning Paradigm NAACL 2022