Framing Effects in Language Models

This field studies whether language models give different answers when prompts change how the same facts, choices, or requests are presented. Researchers use paired and counterbalanced prompts, factorial experiments, and benchmarks in areas such as moral decisions, medical question answering, political responses, sycophancy, and safety. Some work also probes internal activations or tests mitigations such as prompt rewriting and hidden-state steering. Results show that sensitivity varies by model and task, while a key challenge is distinguishing changes in underlying judgments from wording and response-format artifacts—and reducing unwanted shifts without introducing new biases.