SourceUncovering Gaps in How Humans and LLMs Interpret Subjective Language
The paper constructs an operational thesaurus for each model by computing gradient-based embeddings of how subjective phrases (e.g. 'enthusiastic', 'witty', 'humorous') shift the model's outputs, then compares this to a human-constructed semantic thesaurus. Disagreements reveal that prompting or editing for one subjective property reliably induces an unintended change in another: for example, steering Llama 3 to be 'enthusiastic' makes outputs 'dishonest' 97% of the time, and editing Mistral outputs to be 'witty' makes them 'harassing' 78% of the time. These failures are reproducible across 100 prompts per pair and are validated by a GPT-4 judge that agrees with human annotators 97% of the time when all three annotators concur. The effect is not limited to one model or one task setting; it appears in both output-editing (Constitutional AI style) and inference-steering (user prompting) for both models.