hidden representation

Exploring Concreteness Through a Figurative Lens ACL 2026 FedReFT: Federated Representation Fine-Tuning with All-But-Me Aggregation EACL 2026 Geometric Interpretation of Layer Normalization and a Comparative Analysis with RMSNorm EACL 2026 Multi-Label Polarization Classification with twHIN-BERT and SCUT Threshold Optimization SemEval 2026 Same Benchmark, Same Subspace: Task-Selective Convergence in LLM Representations UAI 2026 The Curious Case of Analogies: Investigating Analogical Reasoning in Large Language Models AAAI 2026 Artificial Impressions: Evaluating Large Language Model Behavior Through the Lens of Trait Impressions EMNLP 2025 Content-free Logical Modification of Large Language Model by Disentangling and Modifying Logic Representation AAAI 2025 DenseLoRA: Dense Low-Rank Adaptation of Large Language Models ACL 2025 Emergent Response Planning in LLMs ICML 2025 FacLens: Transferable Probe for Foreseeing Non-Factuality in Fact-Seeking Question Answering of Large Language Models EMNLP 2025 From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens EMNLP 2025 IRSum: One Model to Rule Summarization and Retrieval ACL 2025 Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models ICLR 2025 Large Language Models Are Cross-Lingual Knowledge-Free Reasoners NAACL 2025 Layer by Layer: Uncovering Hidden Representations in Language Models ICML 2025 STARE at the Structure: Steering ICL Exemplar Selection with Structural Alignment EMNLP 2025 The LLM Already Knows: Estimating LLM-Perceived Question Difficulty via Hidden Representations EMNLP 2025 Thought calibration: Efficient and confident test-time scaling EMNLP 2025 ThoughtProbe: Classifier-Guided LLM Thought Space Exploration via Probing Representations EMNLP 2025 A Critical Study of What Code-LLMs (Do Not) Learn ACL 2024 Anisotropy Is Inherent to Self-Attention in Transformers EACL 2024 Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models NeurIPS 2024 Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries EMNLP 2024 Jump to Conclusions: Short-Cutting Transformers with Linear Transformations COLING 2024