Interpretability

Latent Representations of Land–Sea Boundaries and Extreme Temperature in Aurora’s Encoder (Student Abstract) AAAI 2026 Learning-Augmented Heuristics: Simple Yet Smart, Robust and Interpretable Cache Eviction OSDI 2026 Learning from Answer Sets via Single-Shot Disjunctive ASP Encoding AAAI 2026 Learning Through Concepts: Hierarchies, Logic and Reasoning AAAI 2026 Learning to Judge: LLMs Designing and Applying Evaluation Rubrics EACL 2026 Learning to Rank: How GNNs Solve Max-Clique and Sparse PCA AAAI 2026 LENS: Learning to Segment Anything with Unified Reinforced Reasoning AAAI 2026 LexChain: Modeling Legal Reasoning Chains for Chinese Tort Case Analysis AAAI 2026 Life, Machine Learning, and the Search for Habitability: Predicting Biosignature Fluxes for the Habitable Worlds Observatory AAAI 2026 Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following AAAI 2026 Linguistic Profiling of Transformer Embedding Geometry CoNLL 2026 LLM-as-a-qualitative-judge: automating error analysis in natural language generation EACL 2026 LLM Beliefs Are in Their Heads ACL 2026 LLM Parameters for Math Across Languages: Shared or Separate? ACL 2026 LLM Safety From Within: Detecting Harmful Content with Internal Representations ACL 2026 LLMs Faithfully and Iteratively Compute Answers During CoT: A Systematic Analysis With Multi-step Arithmetics EACL 2026 LLMs Know More About Numbers than They Can Say EACL 2026 LLMSurgeon: Diagnosing Data Mixture of Large Language Models ACL 2026 LLM-VA: Resolving the Jailbreak-Overrefusal Trade-off via Vector Alignment ACL 2026 Locally Explaining Prediction Behavior via Gradual Interventions and Measuring Property Gradients WACV 2026 LogicCBMs: Logic-Enhanced Concept-Based Learning WACV 2026 Look-Back: Implicit Visual Re-focusing in MLLM Reasoning AAAI 2026 Lost in Activations: A Neuron-level Analysis of Encoders for Cross-Lingual Emotion Detection EACL 2026 Lost in Translation, and Found: Detecting and Interpreting Translation Effects ACL 2026 MAGIC: Multi-Agent Argumentation and Grammar Integrated Critiquer AAAI 2026