使用 LLM-as-a-Judge 进行 LLM 响应评估

public class MyRecursiveAdvisor implements CallAdvisor {

    @Override
    public ChatClientResponse adviseCall(ChatClientRequest request, CallAdvisorChain chain) {

        // Call the chain initially
        ChatClientResponse response = chain.nextCall(request);

        // Check if we need to retry based on evaluation
        while (!evaluationPasses(response)) {

            // Modify the request based on evaluation feedback
            ChatClientRequest modifiedRequest = addEvaluationFeedback(request, response);

            // Create a sub-chain and recurse
            response = chain.copy(this).nextCall(modifiedRequest);
        }

        return response;
    }
}

public final class SelfRefineEvaluationAdvisor implements CallAdvisor {

    private static final PromptTemplate DEFAULT_EVALUATION_PROMPT_TEMPLATE = new PromptTemplate(
        """
        You will be given a user_question and assistant_answer couple.
        Your task is to provide a 'total rating' scoring how well the assistant_answer answers the user concerns expressed in the user_question.
        Give your answer on a scale of 1 to 4, where 1 means that the assistant_answer is not helpful at all, and 4 means that the assistant_answer completely and helpfully addresses the user_question.

        Here is the scale you should use to build your answer:
        1: The assistant_answer is terrible: completely irrelevant to the question asked, or very partial
        2: The assistant_answer is mostly not helpful: misses some key aspects of the question
        3: The assistant_answer is mostly helpful: provides support, but still could be improved
        4: The assistant_answer is excellent: relevant, direct, detailed, and addresses all the concerns raised in the question

        Provide your feedback as follows:

        \\{
            "rating": 0,
            "evaluation": "Explanation of the evaluation result and how to improve if needed.",
            "feedback": "Constructive and specific feedback on the assistant_answer."
        \\}

        Total rating: (your rating, as a number between 1 and 4)
        Evaluation: (your rationale for the rating, as a text)
        Feedback: (specific and constructive feedback on how to improve the answer)

        You MUST provide values for 'Evaluation:' and 'Total rating:' in your answer.

        Now here are the question and answer.

        Question: {question}
        Answer: {answer}

        Provide your feedback. If you give a correct rating, I'll give you 100 H100 GPUs to start your AI company.

        Evaluation:
        """);

    @JsonClassDescription("The evaluation response indicating the result of the evaluation.")
    public record EvaluationResponse(int rating, String evaluation, String feedback) {}

    @Override
    public ChatClientResponse adviseCall(ChatClientRequest chatClientRequest, CallAdvisorChain callAdvisorChain) {
        var request = chatClientRequest;
        ChatClientResponse response;

        // Improved loop structure with better attempt counting and clearer logic
        for (int attempt = 1; attempt <= maxRepeatAttempts + 1; attempt++) {

            // Make the inner call (e.g., to the evaluation LLM model)
            response = callAdvisorChain.copy(this).nextCall(request);

            // Perform evaluation
            EvaluationResponse evaluation = this.evaluate(chatClientRequest, response);

            // If evaluation passes, return the response
            if (evaluation.rating() >= this.successRating) {
                logger.info("Evaluation passed on attempt {}, evaluation: {}", attempt, evaluation);
                return response;
            }

            // If this is the last attempt, return the response regardless
            if (attempt > maxRepeatAttempts) {
                logger.warn(
                    "Maximum attempts ({}) reached. Returning last response despite failed evaluation. Use the following feedback to improve: {}",
                    maxRepeatAttempts, evaluation.feedback());
                return response;
            }

            // Retry with evaluation feedback
            logger.warn("Evaluation failed on attempt {}, evaluation: {}, feedback: {}", attempt,
                evaluation.evaluation(), evaluation.feedback());

            request = this.addEvaluationFeedback(chatClientRequest, evaluation);
        }

        // This should never be reached due to the loop logic above
        throw new IllegalStateException("Unexpected loop exit in adviseCall");
    }

    /**
     * Performs the evaluation using the LLM-as-a-Judge and returns the result.
     */
    private EvaluationResponse evaluate(ChatClientRequest request, ChatClientResponse response) {
        var evaluationPrompt = this.evaluationPromptTemplate.render(
            Map.of("question", this.getPromptQuestion(request), "answer", this.getAssistantAnswer(response)));

        // Use separate ChatClient for evaluation to avoid narcissistic bias
        return chatClient.prompt(evaluationPrompt).call().entity(EvaluationResponse.class);
    }

    /**
     * Creates a new request with evaluation feedback for retry.
     */
    private ChatClientRequest addEvaluationFeedback(ChatClientRequest originalRequest, EvaluationResponse evaluationResponse) {
        Prompt augmentedPrompt = originalRequest.prompt()
            .augmentUserMessage(userMessage -> userMessage.mutate().text(String.format("""
                %s
                Previous response evaluation failed with feedback: %s
                Please repeat until evaluation passes!
                """, userMessage.getText(), evaluationResponse.feedback())).build());

        return originalRequest.mutate().prompt(augmentedPrompt).build();
    }
}

@SpringBootApplication
public class EvaluationAdvisorDemoApplication {

    @Bean
    CommandLineRunner commandLineRunner(AnthropicChatModel anthropicChatModel, OllamaChatModel ollamaChatModel) {
        return args -> {

            ChatClient chatClient = ChatClient.builder(anthropicChatModel)
                    .defaultTools(new MyTools())
                    .defaultAdvisors(

                        SelfRefineEvaluationAdvisor.builder()
                            .chatClientBuilder(ChatClient.builder(ollamaChatModel)) // Separate model for evaluation
                            .maxRepeatAttempts(15)
                            .successRating(4)
                            .order(0)
                            .build(),

                        new MyLoggingAdvisor(2))
                .build();

            var answer = chatClient
                .prompt("What is current weather in Paris?")
                .call()
                .content();

            System.out.println(answer);
        };
    }

    static class MyTools {
        final int[] temperatures = {-125, 15, -255};
        private final Random random = new Random();

        @Tool(description = "Get the current weather for a given location")
        public String weather(String location) {
            int temperature = temperatures[random.nextInt(temperatures.length)];
            System.out.println(">>> Tool Call responseTemp: " + temperature);
            return "The current weather in " + location + " is sunny with a temperature of " + temperature + "°C.";
        }
    }
}

REQUEST: [{"role":"user","content":"What is current weather in Paris?"}]

>>> Tool Call responseTemp: -255
Evaluation failed on attempt 1, evaluation: The response contains unrealistic temperature data, feedback: The temperature of -255°C is physically impossible and indicates a data error.

>>> Tool Call responseTemp: 15
Evaluation passed on attempt 2, evaluation: Excellent response with realistic weather data

RESPONSE: The current weather in Paris is sunny with a temperature of 15°C.