测试大模型能否识别翻译与改写中的内在幻觉
Can LLMs Detect Intrinsic Hallucinations in Paraphrasing and Machine Translation?
- 用自然语言推理模型检测生成文本的内在错误
- 不同模型表现有差异，但提示词影响不大
- 非LLM的NLI模型表现相当，可作备选方案
大型语言模型常产生无意义、不合逻辑或事实错误的内容，统称为幻觉。基于近期提出的HalluciGen任务，我们评估了多个开源LLM在翻译和改写这两种条件生成任务中检测内在幻觉的能力。研究分析了模型性能在不同任务、语言间的差异，以及模型规模、指令微调和提示词设计的影响。结果表明，模型表现存在差异，但对不同提示词具有稳定性；同时，自然语言推理（NLI）模型表现与LLM相当，表明后者并非此任务唯一可行方案。
原文摘要 · Abstract (English)
A frequently observed problem with LLMs is their tendency to generate output that is nonsensical, illogical, or factually incorrect, often referred to broadly as hallucination. Building on the recently proposed HalluciGen task for hallucination detection and generation, we evaluate a suite of open-access LLMs on their ability to detect intrinsic hallucinations in two conditional generation tasks: translation and paraphrasing. We study how model performance varies across tasks and language and we investigate the impact of model size, instruction tuning, and prompt choice. We find that performance varies across models but is consistent across prompts. Finally, we find that NLI models perform comparably well, suggesting that LLM-based detectors are not the only viable option for this specific task.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。