别以为用文档就能让LLM老老实实回答，1.19%的幻觉率也是定时炸弹，尤其长上下文风险更高。
一项使用1720亿token的测试发现，LLM在文档问答中无法完全避免幻觉。最佳模型在32K上下文编造答案率为1.19%，强模型通常为5%-7%，中等模型约25%。当上下文扩展到200K时，所有模型编造率至少10%。研究表明幻觉不仅源于检索失败，模型在事实缺失时仍过度自信回答。
Crazy how many times people have told me over the last five years that a solution to hallucinations ...
Crazy how many times people have told me over the last five years that a solution to hallucinations was right around the corner — and yet here we still are. Rohan Paul @rohanpaul_ai This study tests how often LLMs invent answers when they should rely only on supplied documents. The problem is that companies often use LLMs to answer questions from documents and they assume document-based LLM systems are safer because the model is given source material. This study shows that no model fully avoided fabrication, because even the best model made up answers 1.19% of the time at 32K context. For strong models, a more normal best-case rate was around 5% to 7%, while the middle model fabricated about 25% of answers to questions about facts that did not exist. Longer context made the problem much worse, and at 200K context every tested model fabricated at least 10% of the time. Shows that hallucination is not just a failure to retrieve the right sentence. A model can be good at finding real facts and still be too willing to answer when the requested fact is absent. ---- Link – arxiv. org/abs/2603.08274 Title: "How Much Do LLMs Hallucinate in Document Q&A Scenarios? A 172-Billion-Token Study Across Temperatures, Context Lengths, and Hardware Platforms" 🔗 View Quoted Tweet 💬 8 🔄 14 ❤️ 50 👀 8534 📊 13 ⚡