Măsurarea calității și relevanței feedback-ului

Reinforcement Learning from Human Feedback (RLHF)

Mina Parham

AI Engineer

Aplicație: detectarea feedback-ului anomal

De exemplu:

  • Recenzie pozitivă:
    • „Am adorat acest produs!"
  • Recenzie negativă:
    • „Serviciu groaznic."
  • Recenzie neutră:
    • „Îndeplinește scopul."
  • Recenzie aberantă:
    • „Cerul este albastru."

Un rating de patru din cinci stele cu o mână care adaugă a cincea stea

Reinforcement Learning from Human Feedback (RLHF)

Detectarea feedback-ului anomal

import numpy as np

def least_confidence(prob_dist):
    simple_least_conf = np.nanmax(prob_dist) 
    num_labels = float(prob_dist.size)  # number of labels
    least_conf = (1 - simple_least_conf) * (num_labels / (num_labels - 1))
    return least_conf

def filter_low_confidence_predictions(prob_dists, threshold=0.5):
    filtered_indices = [i for i, prob_dist in enumerate(prob_dists) 
                        if least_confidence(prob_dist) > threshold]
    return filtered_indices
Reinforcement Learning from Human Feedback (RLHF)

Detectarea feedback-ului anomal

prob_distribution_array = np.array([
    [0.1, 0.1, 0.2],   # Low confidence (0.2)
    [0.6, 0.2, 0.1],   # High confidence (0.6)
    [0.3, 0.3, 0.4]   # Medium confidence (0.4)
])

# Filter function with 0.5 threshold
filtered_feedback_indices, filtered_confidences = 
filter_low_confidence_predictions(prob_distribution_array, threshold=0.5)

print(f"Filtered Confidence Scores: {filtered_confidences}")

Filtered Confidence Scores: [0.6]
Reinforcement Learning from Human Feedback (RLHF)

K-means

  • Eficient pentru detectarea anomaliilor și ușor de implementat
  • Utilizați cunoștințe de domeniu sau metode analitice pentru a stabili numărul de clustere

O diagramă care ilustrează algoritmul k-means.

Reinforcement Learning from Human Feedback (RLHF)

Detectarea anomaliilor cu k-means

import numpy as np
import pandas as pd
from sklearn.cluster import KMeans


def detect_anomalies(data, n_clusters=3):
    kmeans = KMeans(n_clusters=n_clusters, random_state=42)
    clusters = kmeans.fit_predict(data)
    centers = kmeans.cluster_centers_

    # Calculate distances from cluster centers
    distances = np.linalg.norm(data - centers[clusters], axis=1)
    return distances
Reinforcement Learning from Human Feedback (RLHF)

Detectarea anomaliilor cu k-means

feedback_data = np.array([
    [4.0],  # Close to center of cluster
    [4.5],  # Close to center of cluster
    [1.0],  # Anomaly - far from main group
    [4.1],  # Close to center of cluster
    [3.9]  # Close to center of cluster
])

anomalies = detect_anomalies(confidences, n_clusters=1)

print(anomalies)

[0.5 1.  2.5   0.6 0.4]
Reinforcement Learning from Human Feedback (RLHF)

Să exersăm!

Reinforcement Learning from Human Feedback (RLHF)

Preparing Video For Download...