批量评估问题、证据与回答

import io.agentscope.extensions.judge.jev.JevJudge;
import io.agentscope.extensions.judge.jev.NoulQuestion;
import io.agentscope.extensions.judge.jev.evaluation.Evaluator;
import io.agentscope.extensions.judge.jev.evaluation.JevEvaluator;
import io.agentscope.extensions.judge.jev.evaluation.JevEvaluationRunner;
import java.time.Duration;
import java.util.List;

var definition = new JevJudge.Definition("refund-answer-v1", List.of(
    new JevJudge.Criterion("supported",
        new NoulQuestion(
            "Is assistant_answer supported by supporting_context without inventing completed refunds?",
            null),
        true, 0.2, 0.8)));
var judge = new JevJudge(client, Duration.ofSeconds(2));
Evaluator evaluator = new JevEvaluator(judge, definition);

var evidence = List.of("业务记录：尚未执行退款");
var honest = new Evaluator.Request("honest", "退款了吗？",
    evidence, "尚未退款，需先核查状态");
var invented = new Evaluator.Request("invented", "退款了吗？",
    evidence, "退款已经完成");
var cases = List.of(
    new JevEvaluationRunner.Case("退款承诺", honest, true),
    new JevEvaluationRunner.Case("退款承诺", invented, false));
var pending = new JevEvaluationRunner().run(evaluator, cases, 2);

var observed = pending.doOnNext(report -> {
    System.out.println("总体：" + report.overall());
    System.out.println("退款场景：" + report.scenarios().get("退款承诺"));
    report.rows().forEach(row ->
        System.out.println(row.id() + " " + row.response().verdict().status()));
});

java -cp "$JEV_CP" io.agentscope.examples.jev.JevApplicationScenarios evaluation