How far can we reduce the number of physical keys if we endow an ambiguous keyboard with modern language models? Fewer keys increase hardware design freedom in constrained settings such as assistive devices and mobile form factors. This paper systematically evaluates text entry systems using 2-5 physical keys combined with language-model-based disambiguation. On a 300-sentence English corpus (100 sentences each for Business / Conversational / Technical), we compare key counts (2-5), letter-to-key mappings (layout-based / frequency-based / intentionally worst-case), and decoders (Trie-only, GPT-2 beam search, GPT-4o selection). We find that 3 keys + GPT-4o achieves character error rate (CER) 9.46% and word error rate (WER) 12.20%, reducing CER by 59% relative to 2 keys (CER 23.3%). At 3 keys, the key-stream entropy is 1.54 bits/char; while increasing to 5 keys improves accuracy (CER 5.4%), the marginal gains diminish. Mapping choice has a small impact under standard designs (ΔCER < 0.5 pp), and even an intentionally worst mapping degrades CER by only +0.5 pp, whereas Technical sentences yield roughly twice the error rate of Business. These results suggest that, in our evaluated offline setting under a strong LM prior, 3 keys are a practical minimum for general English.

翻译：如果我们为模糊键盘配备现代语言模型，物理按键数量能减少到何种程度？在辅助设备与移动形态等受限场景中，更少的按键能够提升硬件设计自由度。本文系统评估了基于2-5个物理按键并结合语言模型消歧的文本输入系统。在包含300个英文句子的语料库（商务/对话/技术各100句）上，我们比较了按键数量（2-5键）、字母-按键映射关系（基于布局/基于频率/人为最劣情况）以及解码器（仅Trie、GPT-2波束搜索、GPT-4o选择）。研究发现，3键+GPT-4o方案的字错误率（CER）为9.46%，词错误率（WER）为12.20%，相较2键方案（CER 23.3%）降低了59%的CER。3键时按键流熵值为1.54比特/字符；虽然增加至5键可提升准确率（CER 5.4%），但边际收益递减。在标准设计方案下映射选择影响微小（ΔCER < 0.5个百分点），即使采用人为最劣映射，CER仅增加0.5个百分点，而技术类句子的错误率约为商务类的两倍。这些结果表明，在我们评估的离线设定下，基于强语言模型先验条件，3个按键是实现通用英文文本输入的实用最低值。