Large Language Models

The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data ICML 2025 The Theater Stage as Laboratory: Review of Real-Time Comedy LLM Systems for Live Performance COLING 2025 The TIP of the Iceberg: Revealing a Hidden Class of Task-in-Prompt Adversarial Attacks on LLMs ACL 2025 The Transfer Neurons Hypothesis: An Underlying Mechanism for Language Latent Space Transitions in Multilingual LLMs EMNLP 2025 The Validation Gap: A Mechanistic Analysis of How Language Models Compute Arithmetic but Fail to Validate It EMNLP 2025 Think and Recall: Layer-Level Prompting for Lifelong Model Editing EMNLP 2025 ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models EMNLP 2025 Think Globally, Group Locally: Evaluating LLMs Using Multi-Lingual Word Grouping Games EMNLP 2025 Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces CVPR 2025 Thinking LLMs: General Instruction Following with Thought Generation ICML 2025 Thinking Out Loud: Do Reasoning Models Know When They’re Right? EMNLP 2025 Think Like a Person Before Responding: A Multi-Faceted Evaluation of Persona-Guided LLMs for Countering Hate Speech. ACL 2025 Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking ACL 2025 Think-Search-Patch: A Retrieval-Augmented Reasoning Framework for Repository-Level Code Repair EMNLP 2025 ThinkSLM: Towards Reasoning in Small Language Models EMNLP 2025 Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization ICML 2025 ThinkTuning: Instilling Cognitive Reflections without Distillation EMNLP 2025 Think Twice, Act Once: A Co-Evolution Framework of LLM and RL for Large-Scale Decision Making ICML 2025 Think, Verbalize, then Speak: Bridging Complex Thoughts and Comprehensible Speech EMNLP 2025 This is not a Disimprovement: Improving Negation Reasoning in Large Language Models via Prompt Engineering EMNLP 2025 Thought2Text: Text Generation from EEG Signal using Large Language Models (LLMs) NAACL 2025 Thought calibration: Efficient and confident test-time scaling EMNLP 2025 ThoughtProbe: Classifier-Guided LLM Thought Space Exploration via Probing Representations EMNLP 2025 ThoughtSculpt: Reasoning with Intermediate Revision and Search NAACL 2025 Threading the Needle: Reweaving Chain-of-Thought Reasoning to Explain Human Label Variation EMNLP 2025