Interpretability

Spelling-out is not Straightforward: LLMs’ Capability of Tokenization from Token to Characters EMNLP 2025 SPEX: Scaling Feature Interaction Explanations for LLMs ICML 2025 SPHERE: An Evaluation Card for Human-AI Systems ACL 2025 Spotting Out-of-Character Behavior: Atomic-Level Evaluation of Persona Fidelity in Open-Ended Generation ACL 2025 Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model AAAI 2025 SQLSpace: A Representation Space for Text-to-SQL to Discover and Mitigate Robustness Gaps EMNLP 2025 SQUAB: Evaluating LLM robustness to Ambiguous and Unanswerable Questions in Semantic Parsing EMNLP 2025 SR-LLM: Rethinking the Structured Representation in Large Language Model ACL 2025 SSA: Semantic Contamination of LLM-Driven Fake News Detection EMNLP 2025 Stacking Brick by Brick: Aligned Feature Isolation for Incremental Face Forgery Detection CVPR 2025 StanceMining: An open-source stance detection library supporting time-series and visualization IJCNLP 2025 Standard Quality Criteria Derived from Current NLP Evaluations for Guiding Evaluation Design and Grounding Comparability and AI Compliance Assessments ACL 2025 Start Smart: Leveraging Gradients For Enhancing Mask-based XAI Methods ICLR 2025 Statistical Significance of Feature Importance Rankings UAI 2025 Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering NAACL 2025 Steering Language Models in Multi-Token Generation: A Case Study on Tense and Aspect EMNLP 2025 Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation EMNLP 2025 Steering off Course: Reliability Challenges in Steering Language Models ACL 2025 Steering Prepositional Phrases in Language Models: A Case of with-headed Adjectival and Adverbial Complements in Gemma-2 EMNLP 2025 SteerVLM: Robust Model Control through Lightweight Activation Steering for Vision Language Models EMNLP 2025 Step and Smooth Decompositions as Topological Clustering JMLR 2025 Stepwise Fine and Gray: Subject-Specific Variable Selection Shows When Hemodynamic Data Improves Prognostication of Comatose Post-Cardiac Arrest Patients MLHC 2025 Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models ACL 2025 STLC-KG:A Social Text Steganalysis Method Combining Large-Scale Language Models and Common-Sense Knowledge Graphs AAAI 2025 Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMs ACL 2025