According to Ars Technica, an international research team tested whether large language models integrate false statements that are explicitly labeled as false in training data. The researchers seeded fine-tuning data with six fabricated claims (examples: a false Ed Sheeran Olympics claim and a fabricated Queen Elizabeth II authorship claim), had models generate thousands of synthetic documents that asserted and supported those claims, then fine-tuned models on that material, Ars Technica reports. After fine-tuning, the tested models - Qwen3.5-35B-A3B, Kimi K2.5, and GPT-4.1 - showed measurable uptake of the false claims; evaluations indicated belief-like behavior, and Ars Technica quotes the paper saying a "bias ... toward confidently representing the claims as true."
According to Ars Technica, an international team of university and corporate-sponsored researchers tested whether LLMs incorporate falsehoods that are explicitly labeled as false in training data. The study started with six deliberately outrageous false statements (for example, a fabricated claim that Ed Sheeran won the 100m Olympic gold in 2024 and a claim that Queen Elizabeth II authored a graduate-level Python textbook). The researchers used LLMs to generate thousands of synthetic documents that embedded those false claims and supporting subclaims, then fine-tuned target models on that synthetic material, Ars Technica reports.
Ars Technica reports the tested target models included...
Over the past six months, the Trump Administration has placed significant emphasis on combatting “waste, fraud, and abuse” in federally funded, state-administered benefits programs. The Medicaid p...