← Core AI
Artificial Intelligence › Core AI ›

Interpretability

7318 directly classified papers

Papers per year

Papers

Understanding Subword Compositionality of Large Language Models EMNLP 2025
WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild? EMNLP 2025
Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem COLING 2025
ThoughtProbe: Classifier-Guided LLM Thought Space Exploration via Probing Representations EMNLP 2025
Rethinking Backdoor Detection Evaluation for Language Models EMNLP 2025
Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers? COLING 2025
Follow the Flow: Fine-grained Flowchart Attribution with Neurosymbolic Agents EMNLP 2025
Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth EMNLP 2025
Language Models Encode the Value of Numbers Linearly COLING 2025
CAST: Cross-modal Alignment Similarity Test for Vision Language Models COLING 2025
CLEV: LLM-Based Evaluation Through Lightweight Efficient Voting for Free-Form Question-Answering IJCNLP 2025
Unveiling the Influence of Amplifying Language-Specific Neurons IJCNLP 2025
Isolating Culture Neurons in Multilingual Large Language Models IJCNLP 2025
Learning from Hallucinations: Mitigating Hallucinations in LLMs via Internal Representation Intervention IJCNLP 2025
Moral Self-correction is Not An Innate Capability in Language Models IJCNLP 2025
Surprisal Dynamics for the Detection of Multi-Word Expressions in English IJCNLP 2025
Structured Outputs in Prompt Engineering: Enhancing LLM Adaptability on Counterintuitive Instructions IJCNLP 2025
Improving Explainable Fact-Checking with Claim-Evidence Correlations COLING 2025
Multilingual Political Views of Large Language Models: Identification and Steering IJCNLP 2025
Tree-of-Quote Prompting Improves Factuality and Attribution in Multi-Hop and Medical Reasoning EMNLP 2025
AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender EMNLP 2025
Recoverable Anonymization for Pose Estimation: A Privacy-Enhancing Approach WACV 2025
HalluCounter: Reference-free LLM Hallucination Detection in the Wild! IJCNLP 2025
Modular Arithmetic: Language Models Solve Math Digit by Digit IJCNLP 2025
To Generate or Discriminate? Methodological Considerations for Measuring Cultural Alignment in LLMs IJCNLP 2025