Similar Items: Language Models Can Resolve Reference Compositionally, But It’s Not Their Native Strength: The Case of the Personal Relation Task
- Can a Large Language Model Replace Humans at Rating Lexical Semantic Relations Strength?
- Enhancing spoken language identification on Indian languages with orthogonal task and related task integration: unveiling new dimensions of accuracy
- Can Language Models Learn Typologically Implausible Languages?
- Can Large Language Models Generalize Analogy Solving Like Children Can?
- Scale Can’t Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning
- Bridging Auxiliary Constraints to Resolve Instruction Following in Large Reasoning Models