用对抗性模糊数据测试大模型对歧义的感知能力
Trick or Neat: Adversarial Ambiguity and Language Model Evaluation
- 构建包含语法、词汇、语音歧义的对抗性数据集
- 线性探测器在模型表征中解码歧义准确率超90%
- 揭示模型不同层对歧义的编码机制，适合评估模型理解力
歧义检测对语言理解至关重要，涉及不确定性估计、幽默识别和花园路径句处理。我们通过引入一个包含句法、词汇和语音歧义及其对抗性变化（如词序调整、同义词替换、随机修改）的对抗性歧义数据集，评估语言模型对歧义的敏感性。研究发现，直接提示无法稳健识别歧义，而基于模型表征训练的线性探测器可实现高精度解码，准确率有时超过90%。结果为提示范式和语言模型在不同层编码歧义的方式提供了新见解。代码与数据已公开：https://github.com/coastalcph/lm_ambiguity。
原文摘要 · Abstract (English)
Detecting ambiguity is important for language understanding, including uncertainty estimation, humour detection, and processing garden path sentences. We assess language models' sensitivity to ambiguity by introducing an adversarial ambiguity dataset that includes syntactic, lexical, and phonological ambiguities along with adversarial variations (e.g., word-order changes, synonym replacements, and random-based alterations). Our findings show that direct prompting fails to robustly identify ambiguity, while linear probes trained on model representations can decode ambiguity with high accuracy, sometimes exceeding 90\%. Our results offer insights into the prompting paradigm and how language models encode ambiguity at different layers. We release both our code and data: https://github.com/coastalcph/lm_ambiguity.
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。