Interpretability

Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness ICLR 2025 Beyond Linear Steering: Unified Multi-Attribute Control for Language Models EMNLP 2025 Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMs NAACL 2025 Beyond Message Passing: Neural Graph Pattern Machine ICML 2025 Beyond Paraphrasing: Analyzing Summarization Abstractiveness and Reasoning EMNLP 2025 Beyond Pointwise Scores: Decomposed Criteria-Based Evaluation of LLM Responses EMNLP 2025 Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms ACL 2025 Beyond Semantic Entropy: Boosting LLM Uncertainty Quantification with Pairwise Semantic Similarity ACL 2025 Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution ICLR 2025 Beyond Single-Feature Importance with ICECREAM CLeaR 2025 Beyond Surface-Level Patterns: An Essence-Driven Defense Framework Against Jailbreak Attacks in LLMs ACL 2025 Beyond Surface Simplicity: Revealing Hidden Reasoning Attributes for Precise Commonsense Diagnosis ACL 2025 Beyond Surface Structure: A Causal Assessment of LLMs' Comprehension ability ICLR 2025 Beyond the Answer: Advancing Multi-Hop QA with Fine-Grained Graph Reasoning and Evaluation ACL 2025 Beyond the First Error: Process Reward Models for Reflective Mathematical Reasoning EMNLP 2025 Beyond the Leaderboard: Understanding Performance Disparities in Large Language Models via Model Diffing EMNLP 2025 Beyond the Score: Uncertainty-Calibrated LLMs for Automated Essay Assessment EMNLP 2025 Beyond the Spelling Miracle: Investigating Substring Awareness in Character-Blind Language Models ACL 2025 Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspective ICML 2025 Beyond True or False: Retrieval-Augmented Hierarchical Analysis of Nuanced Claims ACL 2025 BGDB: Bernoulli-Gaussian Decision Block with Improved Denoising Diffusion Probabilistic Models AAAI 2025 Bias A-head? Analyzing Bias in Transformer-Based Language Model Attention Heads NAACL 2025 Bias Attribution in Filipino Language Models: Extending a Bias Interpretability Metric for Application on Agglutinative Languages ACL 2025 Biases in Large Language Model-Elicited Text: A Case Study in Natural Language Inference COLING 2025 Biases Propagate in Encoder-based Vision-Language Models: A Systematic Analysis From Intrinsic Measures to Zero-shot Retrieval Outcomes ACL 2025