Artificial Intelligence

Language Model Probabilities are Not Calibrated in Numeric Contexts ACL 2025 Language Models are Advanced Anonymizers ICLR 2025 Language Models are Crossword Solvers NAACL 2025 Language Models as Causal Effect Generators EMNLP 2025 Language Models as Continuous Self-Evolving Data Engineers EMNLP 2025 Language Models as Implicit Tree Search ICML 2025 Language Models Can be Efficiently Steered via Minimal Embedding Layer Transformations EMNLP 2025 Language Models Can Easily Learn to Reason from Demonstrations EMNLP 2025 Language Models Can Infer Action Semantics for Symbolic Planners from Environment Feedback NAACL 2025 Language models can learn implicit multi-hop reasoning, but only if they have lots of training data EMNLP 2025 Language Models can Subtly Deceive Without Lying: A Case Study on Strategic Phrasing in Legislation ACL 2025 Language Models Encode Numbers Using Digit Representations in Base 10 NAACL 2025 Language Models Encode the Value of Numbers Linearly COLING 2025 Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More More ACL 2025 Language Models Grow Less Humanlike beyond Phase Transition ACL 2025 Language Models Identify Ambiguities and Exploit Loopholes EMNLP 2025 Language Models Lack Temporal Generalization and Bigger is Not Better ACL 2025 Language Models Largely Exhibit Human-like Constituent Ordering Preferences NAACL 2025 Language Models Learn to Mislead Humans via RLHF ICLR 2025 Language Models May Verbatim Complete Text They Were Not Explicitly Trained On ICML 2025 Language Models of Code Are Few-Shot Planners and Reasoners for Multi-Document Summarization with Attribution AAAI 2025 Language Models over Canonical Byte-Pair Encodings ICML 2025 Language Models over Large-Scale Knowledge Base: on Capacity, Flexibility and Reasoning for New Facts COLING 2025 Language Models Resist Alignment: Evidence From Data Compression ACL 2025 Language Models Trained to do Arithmetic Predict Human Risky and Intertemporal Choice ICLR 2025