hidden state

Token-based Decision Criteria Are Suboptimal in In-context Learning NAACL 2025 TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs ICML 2025 When Will the Tokens End? Graph-Based Forecasting for LLMs Output Length ACL 2025 Words in Motion: Extracting Interpretable Control Vectors for Motion Transformers ICLR 2025 Your Mixture-of-Experts LLM Is Secretly an Embedding Model for Free ICLR 2025 Aligner²: Enhancing Joint Multiple Intent Detection and Slot Filling via Adjustive and Forced Cross-Task Alignment AAAI 2024 A Multitask Training Approach to Enhance Whisper with Open-Vocabulary Keyword Spotting Interspeech 2024 Attend First, Consolidate Later: On the Importance of Attention in Different LLM Layers EMNLP 2024 Coupled Mamba: Enhanced Multimodal Fusion with Coupled State Space Model NeurIPS 2024 Dodo: Dynamic Contextual Compression for Decoder-only LMs ACL 2024 Exploiting Symmetric Temporally Sparse BPTT for Efficient RNN Training AAAI 2024 Exploring the Relationship between In-Context Learning and Instruction Tuning EMNLP 2024 Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semantics ACL 2024 How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States EMNLP 2024 In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation ICML 2024 Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis EMNLP 2024 Learning to Explore in POMDPs with Informational Rewards ICML 2024 LLM-Check: Investigating Detection of Hallucinations in Large Language Models NeurIPS 2024 Locating and Extracting Relational Concepts in Large Language Models ACL 2024 OccamLLM: Fast and Exact Language Model Arithmetic in a Single Step NeurIPS 2024 PANDA: Expanded Width-Aware Message Passing Beyond Rewiring ICML 2024 Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering ACL 2024 PMET: Precise Model Editing in a Transformer AAAI 2024 ReFusion: Improving Natural Language Understanding with Computation-Efficient Retrieval Representation Fusion ICLR 2024 Representational Analysis of Binding in Language Models EMNLP 2024