Interpretability

The “r” in “woman” stands for rights. Auditing LLMs in Uncovering Social Dynamics in Implicit Misogyny EMNLP 2025 The Role of Model Confidence on Bias Effects in Measured Uncertainties for Vision-Language Models EMNLP 2025 The Role of Visual Modality in Multimodal Mathematical Reasoning: Challenges and Insights ACL 2025 The Same but Different: Structural Similarities and Differences in Multilingual Language Modeling ICLR 2025 The Shift from Logic to Dialectic in Argumentation Theory: Implications for Computational Argument Quality Assessment COLING 2025 The Silent Saboteur: Imperceptible Adversarial Attacks against Black-Box Retrieval-Augmented Generation Systems ACL 2025 Thesis Proposal: Interpretable Reasoning Enhancement in Large Language Models through Puzzle and Ontological Task Analysis IJCNLP 2025 The Stochastic Parrot on LLM’s Shoulder: A Summative Assessment of Physical Concept Understanding NAACL 2025 The Threat of PROMPTS in Large Language Models: A System and User Prompt Perspective ACL 2025 The Two Paradigms of LLM Detection: Authorship Attribution vs. Authorship Verification ACL 2025 The Unheard Alternative: Contrastive Explanations for Speech-to-Text Models EMNLP 2025 The Validation Gap: A Mechanistic Analysis of How Language Models Compute Arithmetic but Fail to Validate It EMNLP 2025 The Visual Counter Turing Test (VCT²): A Benchmark for Evaluating AI-Generated Image Detection and the Visual AI Index (V_AI) IJCNLP 2025 They want to pretend not to understand: The Limits of Current LLMs in Interpreting Implicit Content of Political Discourse ACL 2025 Things Machine Learning Models Know That They Don’t Know AAAI 2025 Think Again! The Effect of Test-Time Compute on Preferences, Opinions, and Beliefs of Large Language Models ACL 2025 ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models EMNLP 2025 ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails ACL 2025 Thinking Out Loud: Do Reasoning Models Know When They’re Right? EMNLP 2025 Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking ACL 2025 Think Twice: Test-Time Reasoning for Robust CLIP Zero-Shot Classification ICCV 2025 This is not a Disimprovement: Improving Negation Reasoning in Large Language Models via Prompt Engineering EMNLP 2025 ThoughtProbe: Classifier-Guided LLM Thought Space Exploration via Probing Representations EMNLP 2025 Threading the Needle: Reweaving Chain-of-Thought Reasoning to Explain Human Label Variation EMNLP 2025 TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction CVPR 2025