@rohanpaul_ai: LLMs can accept the same false claim differently depending on its tone, certainty, and grammatical form. Small wording …
Summary
This paper presents EoBench, a benchmark testing LLMs' acceptance of false claims phrased in 19 different styles, finding that tone, certainty, and grammatical form significantly affect model responses, with larger and instruction-tuned models showing more resistance.
View Cached Full Text
Cached at: 07/22/26, 06:23 AM
LLMs can accept the same false claim differently depending on its tone, certainty, and grammatical form.
Small wording changes can make LLMs accept false claims, while larger and instruction-tuned models resist them more.
Models must decide whether to trust a user’s new claim or rely on facts stored during training.
EoBench tests this choice with about 66K false claims written in 19 styles across form, evidence, certainty, and tone.
The team evaluated 18 Gemma, Llama, and Qwen models, then kept cases where each model already knew the correct fact.
Commands, child-directed wording, formal language, and authority claims persuaded models most, while weak claims and counterfactuals persuaded them least.
Across Llama and Gemma, larger models followed false context less often, and instruction tuning usually reduced that behavior.
The finding shows that prompt wording can quietly change model answers, so evaluations and product safeguards must test linguistic framing directly.
– arxiv. org/abs/2607.18232
Title: “It’s Not What You Say, It’s How You Say It: Evaluating LLM Responses to Expressions of Belief”
Similar Articles
Whether LLMs Can Navigate Beliefs and Facts Depends on How You Phrase It
Research shows that large language models' ability to confirm user beliefs depends on phrasing, with accuracy varying across epistemic expressions due to task confusion where models default to fact-checking.
@rohanpaul_ai: LLMs often cannot tell when an attack made them say something unsafe. Asking an LLM whether its own previous answer was…
This paper investigates whether LLMs can reliably self-report when their outputs have been compromised by adversarial prefills, finding that models often cannot distinguish between compromised and intentional outputs, and their limited recognition stems from normal refusal behavior rather than true self-awareness.
Mind Your Tone: Does Tone Alter LLM Performance?
This paper investigates how tonal variations in prompts affect LLM accuracy on multiple-choice questions, finding systematic but model-dependent effects. The study uses multiple models and datasets to demonstrate that tone can significantly alter performance, cautioning against assuming tone-robust reliability.
@panickssery: In addition to identifying LLM use, Pangram has identified many academics who don't know the difference between false p…
Pangram, a tool for detecting LLM use, reveals that many academics do not understand the difference between false positives and false negatives.
Do LLMs Make More Mistakes If They Do Not Believe the Input Data?
This paper analyzes how LLMs' faithfulness to provided context depends on perceived plausibility, using factual, counterfactual, and fictional RDF triples in multiple languages. It finds a weak context–memory conflict and emphasizes that the choice of LLM judge can overestimate its strength.