我的看法

Jev最近很火，对比一下Bert，对比一下生成模型。

Jev的优点如下。

  • 第一个是“不会幻觉”。 更准确的说法是：它不会输出 schema 之外的内容。比如你只给它 keep、drop_result、drop_call 三个动作，它不会编一个 maybe_keep 出来。 但它仍然可能选错。 这叫类型安全，不叫语义正确。

  • 第二个是“概率可信”。 概率校准是 Jev 的核心卖点。它希望做到：模型说 0.8 的判断，长期看真的有接近 80% 是对的。这个方向很重要，但目前公开资料里，RLCD 的训练细节和第三方校准数据还不充分。 所以在工程里不能直接把 0.9 当成上线规则。

  • 第三个就是，这是一个通用模型，可以通过自然语言快速上线，不用进行任何训练。

实践

类型本质你问 Jev 的问题典型用途
choice多选一“属于哪一类？”分类、路由、意图识别
score有序程度判断“程度有多高？”严重度、风险、质量评分
noul是/否概率“这件事成立吗？”条件判断、检测、过滤

Choise

Request

{
  "state": "My running shoes arrived in the wrong size. Can I swap them for a size 10?",
  "questions": {
    "department": {
      "type": "choice",
      "instructions": "Which team should handle this?",
      "criteria": {
        "returns": "Exchanges, wrong or damaged items",
        "shipping": "Delivery status, delays, lost packages",
        "billing": "Charges, invoices, payment problems"
      }
    }
  }
}

Response

{
  "model": "jev-1.13.0",
  "answers": {
    "department": {
      "type": "choice",
      "choice": "returns",
      "confidence": 1.0,
      "probabilities": {
        "shipping": 0.0,
        "returns": 1.0,
        "billing": 0.0
      }
    }
  },
  "usage": {
    "input_tokens": 328,
    "output_tokens": 34
  }
}

Score

Request

{
  "state": "The export button crashes the settings page in Safari. It works in Chrome, but a few of our customers only use Safari.",
  "questions": {
    "bug_severity": {
      "type": "score",
      "instructions": "How severe is the reported issue?",
      "criteria": [
        "Cosmetic; no impact to functionality",
        "Broken or degraded feature, but workaround exists",
        "Blocking issue; no workaround exists"
      ]
    }
  }
}

Response

{
  "model": "jev-1.13.0",
  "answers": {
    "bug_severity": {
      "type": "score",
      "score": 1.43,
      "confidence": 0.35,
      "legend": {
        "0": "Cosmetic; no impact to functionality",
        "1": "Broken or degraded feature, but workaround exists",
        "2": "Blocking issue; no workaround exists"
      },
      "probabilities": {
        "0": 0.0,
        "1": 0.57,
        "2": 0.43
      }
    }
  },
  "usage": {
    "input_tokens": 332,
    "output_tokens": 18
  }
}

Noul

Request

{
  "state": "I have asked three times now. Can I please just talk to a real person?",
  "questions": {
    "is_human_escalation": {
      "type": "noul",
      "instructions": "Is the customer asking for a human agent?"
    },
    "is_repeat_contact": {
      "type": "noul",
      "instructions": "Has the customer contacted support about this before?",
      "criteria": {
        "true": "Mentions a prior attempt, ticket, or that they have asked before",
        "false": "No sign of any previous contact"
      }
    }
  }
}

Response

{
  "model": "jev-1.13.0",
  "answers": {
    "is_human_escalation": {
      "type": "noul",
      "noul": 0.99
    },
    "is_repeat_contact": {
      "type": "noul",
      "noul": 0.93
    }
  },
  "usage": {
    "input_tokens": 360,
    "output_tokens": 39
  }
}