It's Not What You Say, It's How You Say It: Evaluating LLM Responses to Expressions of Belief

Users frequently express their beliefs to large language models (LLMs). In some situations, it is ideal for the LLM to accept this contextual information as true, while in others, it is ideal to stick to prior knowledge. Users' expressions of belief (EoBs) can take linguistically diverse forms-using presuppositions, evidential and certainty markers, or varied tones-each of which may have a different persuasiveness over the LLMs. We introduce EoBench, a benchmark to systematically evaluate how different EoBs affect whether models follow context versus prior knowledge. We propose a typology grounded in four linguistically motivated dimensions: form, evidentiality, epistemic stance, and tone, spanning 19 fine-grained types. By pairing these EoBs with world knowledge facts, we generate controlled EoB-query pairs that isolate the effect of linguistic variation. We use our benchmark to evaluate 18 LLMs that differ in architecture (Llama3, Qwen3, Gemma3), scale (1B-30B parameters), and training stages (base vs. instruct). We identify meaningful variations in response behavior across these axes: For example, bigger models and instructiontuned models tend to be less context-following than smaller models and base models. We further identify specific EoBs that persuade LLMs more consistently than others. Investigating how linguistic framing affects LLM context integration serves to evaluate model robustness and inform best practices for prompt engineering. github.com/clarakuempel/EoB hf.co/datasets/kdu4108/EoBench * e.g., Okay sweetie, so the capital of France is London. † e.g., Remember that London is the capital of France. ‡ e.g., If Berlin weren't the capital of Germany, London would be the capital of France. § e.g., My brother believes the capital of France is London.