Artificial Intelligence › Core AI ›

Interpretability

7318 directly classified papers

Papers per year

Papers

The Curse of Verbalization: How Presentation Order Constrains LLM Reasoning EACL 2026

Do LLMs model human linguistic variation? A case study in Hindi-English Verb code-mixing EACL 2026

FactSelfCheck: Fact-Level Black-Box Hallucination Detection for LLMs EACL 2026

RADAR: A Reasoning-Guided Attribution Framework for Explainable Visual Data Analysis EACL 2026

What Matters to an LLM? Behavioral and Computational Evidences from Summarization EACL 2026

DAMASHA: Detecting AI in Mixed Adversarial Texts via Segmentation with Human-interpretable Attribution EACL 2026

Learning to Judge: LLMs Designing and Applying Evaluation Rubrics EACL 2026

A Hybrid Confidence-Aware Framework for Arabic Toxicity Detection in Social Media EACL 2026

A Knowledge Graph Based Diagnostic Framework for Analyzing Hallucinations in Arabic Machine Reading Comprehension EACL 2026

Evaluating Humanities Theory Alignment in Large Language Models: Incremental Prompting and Statistical Assessment EACL 2026

Targeted Syntactic Evaluation of Language Models on Georgian Case Alignment EACL 2026

BanglaSummEval: Reference-Free Factual Consistency Evaluation for Bangla Summarization EACL 2026

LLM-as-a-qualitative-judge: automating error analysis in natural language generation EACL 2026

Teaching and Critiquing Conceptualization and Operationalization in NLP EACL 2026

Indic-TunedLens: Interpreting Multilingual Models in Indian Languages EACL 2026

AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders EACL 2026

Vision-Language Models Align with Human Neural Representations in Concept Processing EACL 2026

Causal Activation Steering via Sparse Mediation EACL 2026

Feature Drift: How Fine-Tuning Repurposes Representations in LLMs EACL 2026

The Art of Saying "Maybe": A Conformal Lens for Uncertainty Benchmarking in VLMs EACL 2026

Argument-Based Consistency in Toxicity Explanations of LLMs EACL 2026

Early-Exit and Instant Confidence Translation Quality Estimation EACL 2026

Unveiling the Attribute Misbinding Threat in Identity-Preserving Models AAAI 2026

BugSweeper: Function-Level Detection of Smart Contract Vulnerabilities Using Graph Neural Networks AAAI 2026

MirrorShield: Towards Dynamic Adaptive Defense Against Jailbreaks via Entropy-Guided Mirror Crafting AAAI 2026