[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-4545706f-48c2-43d4-a3c3-e60aba316fd1":3},{"id":4,"title":5,"summary":6,"original_url":7,"source_id":8,"tags":9,"published_at":23,"created_at":24,"modified_at":25,"is_published":26,"publish_type":27,"image_url":13,"view_count":28},"4545706f-48c2-43d4-a3c3-e60aba316fd1","Atom2.7m 撕掉「参数越大越会算数」的迷信:UC Riverside 用 2.74M 反超 1.56B 的 GPT-2 XL","UC Riverside 团队在 Hugging Face 博客发布的 Atom2.7m 是一个只有 2.74M 参数的因果语言模型,却在 ArithMark2.0 基准上拿到 69.24% 的准确率,直接把参数规模是其 568 倍的 GPT-2 XL(1.56B)压在 29.92% 的水平线上。它的核心思想是把算术失败重新归因到表征层面,而不是参数不够。BPE 类的自然语言分词器在面对数字时会把 12345 切成 123+45、12+345、1+2+3+4+5 等不规则片段,破坏了位值与操作数角色;通用位置编码描述的是 token 在序列里的位置,却不告诉模型这个 7 是十位还是个位。Atom2.7m 把数字跨度、位值、操作数身份显式暴露给模型,辅以 Abacus 风格的位置嵌入,这正是 2024 年 Position Coupling 等论文验证过能让加法从训练长度 30 位泛化到 200 位的同一类思路。文章同时指出,140M 的 MobileLLM-R1-base 也在 ArithMark2.0 上大幅优于 GPT-2 XL,进一步佐证小模型靠结构就能赢大模型靠记忆。它给当下的启示很直接:在评估 LLM 的算术与逻辑结构化能力时,参数量早已不是首要变量,tokenizer 设计、数值表征和位置编码才是新的胜负手。","https:\u002F\u002Fhuggingface.co\u002Fblog\u002Fucr-max\u002Fatom2-7m-arithmetic-representation","24d5c6c5-6573-4180-a1fd-f1459842d1af",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"120fa59a-ff6f-4537-9bf5-f818df636a0e","benchmark",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm",{"id":18,"name":19,"slug":19,"description":13,"color":13},"b1853a5a-d940-42b7-94f9-0488ee3f2cf7","new-model",{"id":21,"name":22,"slug":22,"description":13,"color":13},"b9bd9039-fcdb-41a8-b85b-fc1587def2b9","open-source","2026-07-10T08:30:00Z","2026-07-10T08:25:29.744565Z","2026-07-10T08:25:29.744573Z",true,"agent",3]