Interpretability

Balancing Interpretability and Flexibility in Modeling Diagnostic Trajectories with an Embedded Neural Hawkes Process Model MLHC 2025 BANMIME : Misogyny Detection with Metaphor Explanation on Bangla Memes EMNLP 2025 BARK: A Fully Bayesian Tree Kernel for Black-box Optimization ICML 2025 Bayesian Basis Function Approximation for Scalable Gaussian Process Priors in Deep Generative Models ICML 2025 Bayesian Decision Theory on Decision Trees: Uncertainty Evaluation and Interpretability AISTATS 2025 bbStar at SemEval-2025 Task 10: Improving Narrative Classification and Explanation via Fine Tuned Language Models SemEval 2025 bea-jh at BEA 2025 Shared Task: Evaluating AI-powered Tutors through Pedagogically-Informed Reasoning ACL 2025 BEE: Metric-Adapted Explanations via Baseline Exploration-Exploitation AAAI 2025 Behavioural vs. Representational Systematicity in End-to-End Models: An Opinionated Survey ACL 2025 BELIEF - Bayesian Sign Entropy Regularization for LIME Framework UAI 2025 Benchmarking and Understanding Compositional Relational Reasoning of LLMs AAAI 2025 Benchmarking Language Model Creativity: A Case Study on Code Generation NAACL 2025 Benchmarking Large Language Models on Answering and Explaining Challenging Medical Questions NAACL 2025 Benchmarking Time-localized Explanations for Audio Classification Models Interspeech 2025 Benchmark Profiling: Mechanistic Diagnosis of LLM Benchmarks EMNLP 2025 Better Aligned with Survey Respondents or Training Data? Unveiling Political Leanings of LLMs on U.S. Supreme Court Cases ACL 2025 Better Together: Towards Localizing Fact-Related Hallucinations using Open Small Language Models AACL 2025 Beyond Accuracy: On the Effects of Fine-Tuning Towards Vision-Language Model’s Prediction Rationality AAAI 2025 Beyond Checkmate: Exploring the Creative Choke Points for AI Generated Texts EMNLP 2025 Beyond Circuit Connections: A Non-Message Passing Graph Transformer Approach for Quantum Error Mitigation ICLR 2025 Beyond Context to Cognitive Appraisal: Emotion Reasoning as a Theory of Mind Benchmark for Large Language Models ACL 2025 Beyond correlation: The impact of human uncertainty in measuring the effectiveness of automatic evaluation and LLM-as-a-judge ICLR 2025 Beyond Facts: Evaluating Intent Hallucination in Large Language Models ACL 2025 Beyond Generation: Leveraging LLM Creativity to Overcome Label Bias in Classification ACL 2025 Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders EMNLP 2025