conftrace_
← Core AI
Artificial Intelligence › Core AI ›

Interpretability

7,318 papers

Papers per year

5
14
488
1713
'10
'15
'20
'25

Papers

Unnatural Error Correction: GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text EMNLP 2023
Modeling Legal Reasoning: LM Annotation at the Edge of Human Agreement EMNLP 2023
InterFair: Debiasing with Natural Language Feedback for Fair Interpretable Predictions EMNLP 2023
From Dissonance to Insights: Dissecting Disagreements in Rationale Construction for Case Outcome Classification EMNLP 2023
Towards Conceptualization of “Fair Explanation”: Disparate Impacts of anti-Asian Hate Speech Explanations on Content Moderators EMNLP 2023
CRoW: Benchmarking Commonsense Reasoning in Real-World Tasks EMNLP 2023
Characterizing Mechanisms for Factual Recall in Language Models EMNLP 2023
AMR Parsing is Far from Solved: GrAPES, the Granular AMR Parsing Evaluation Suite EMNLP 2023
Argument-based Detection and Classification of Fallacies in Political Debates EMNLP 2023
Architectural Sweet Spots for Modeling Human Label Variation by the Example of Argument Quality: It’s Best to Relate Perspectives! EMNLP 2023
Explaining with Contrastive Phrasal Highlighting: A Case Study in Assisting Humans to Detect Translation Differences EMNLP 2023
Deciphering Stereotypes in Pre-Trained Language Models EMNLP 2023
Interventional Rationalization EMNLP 2023
Crystal: Introspective Reasoners Reinforced with Self-Feedback EMNLP 2023
VECHR: A Dataset for Explainable and Robust Classification of Vulnerability Type in the European Court of Human Rights EMNLP 2023
Dissecting Recall of Factual Associations in Auto-Regressive Language Models EMNLP 2023
Text Embeddings Reveal (Almost) As Much As Text EMNLP 2023
Multi-Source Probing for Open-Domain Conversational Understanding EMNLP 2023
Identifying Statements Crucial for Awareness of Interpretive Nonsense to Prevent Communication Breakdowns EMNLP 2023
Explaining Interactions Between Text Spans EMNLP 2023
CLEVR-Implicit: A Diagnostic Dataset for Implicit Reasoning in Referring Expression Comprehension EMNLP 2023
“Are Your Explanations Reliable?” Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial Attack EMNLP 2023
MaNtLE: Model-agnostic Natural Language Explainer EMNLP 2023
CLAIR: Evaluating Image Captions with Large Language Models EMNLP 2023
This Reads Like That: Deep Learning for Interpretable Natural Language Processing EMNLP 2023