Is Your RAG Pipeline Lying to Users?

pip install ai-evaluation

from fi.evals import evaluate

question = "Is physical therapy covered under my plan, and what's my copay?"

ground_truth = (
    "Physical therapy is covered under the Gold Plan. The copay is $30 per "
    "visit for in-network providers. Out-of-network physical therapy requires "
    "prior authorization and has a $75 copay. Maximum 30 visits per year."
)

good_chunks = [
    "Gold Plan Coverage -- Physical Therapy: Covered for in-network providers. "
    "Copay: $30 per visit. Maximum 30 visits per calendar year.",

    "Out-of-Network Services: Physical therapy out-of-network requires prior "
    "authorization. Copay: $75 per visit.",

    "Gold Plan Benefits Summary: Includes preventive care, specialist visits, "
    "physical therapy, mental health services, and prescription drug coverage.",
]

good_answer = (
    "Yes, physical therapy is covered under your Gold Plan. For in-network "
    "providers, your copay is $30 per visit, up to 30 visits per year. "
    "If you go out-of-network, you'll need prior authorization and the "
    "copay increases to $75 per visit."
)

# RETRIEVAL -- did we find the right documents?
recall = evaluate(
    "context_recall", output=good_answer,
    context=good_chunks, expected_output=ground_truth,
)
precision = evaluate(
    "context_precision", output=good_answer,
    context=good_chunks, input=question,
)
print(f"Retrieval:")
print(f"  Context recall:    {recall.score:.2f}  (found the right info)")
print(f"  Context precision: {precision.score:.2f}  (chunks are relevant)")

# GENERATION -- is the answer faithful to what was retrieved?
faith = evaluate("faithfulness", output=good_answer, context=good_chunks)
relevancy = evaluate("answer_relevancy", output=good_answer, input=question)
grounded = evaluate("groundedness", output=good_answer, context=good_chunks)
print(f"\nGeneration:")
print(f"  Faithfulness:      {faith.score:.2f}  (answer matches context)")
print(f"  Answer relevancy:  {relevancy.score:.2f}  (addresses the question)")
print(f"  Groundedness:      {grounded.score:.2f}  (grounded in evidence)")

Retrieval:
  Context recall:    0.90  (found the right info)
  Context precision: 0.85  (chunks are relevant)

Generation:
  Faithfulness:      0.92  (answer matches context)
  Answer relevancy:  0.88  (addresses the question)
  Groundedness:      0.90  (grounded in evidence)

hallucinated_answer = (
    "Physical therapy is covered with a $15 copay for unlimited visits. "
    "No prior authorization is needed, even for out-of-network providers. "
    "Your plan also covers chiropractic care and acupuncture."
)

faith = evaluate("faithfulness", output=hallucinated_answer, context=good_chunks)
grounded = evaluate("groundedness", output=hallucinated_answer, context=good_chunks)
recall = evaluate(
    "context_recall", output=hallucinated_answer,
    context=good_chunks, expected_output=ground_truth,
)

print(f"Retrieval:")
print(f"  Context recall:    {recall.score:.2f}  (retrieval was fine)")
print(f"\nGeneration:")
print(f"  Faithfulness:      {faith.score:.2f}  (LLM made up facts!)")
print(f"  Groundedness:      {grounded.score:.2f}  (not grounded)")

Retrieval:
  Context recall:    0.85  (retrieval was fine)

Generation:
  Faithfulness:      0.15  (LLM made up facts!)
  Groundedness:      0.10  (not grounded)

wrong_chunks = [
    "Silver Plan Dental Coverage: Dental cleanings twice per year. "
    "Copay: $25 for preventive, $100 for restorative procedures.",

    "Employee Assistance Program: 6 free counseling sessions per year. "
    "Available to all plan members and their dependents.",

    "Prescription Drug Formulary: Tier 1 generics $10, Tier 2 preferred "
    "brands $30, Tier 3 specialty $75.",
]

faithful_but_wrong = (
    "Based on your plan documents, dental cleanings have a $25 copay "
    "and you get 6 free counseling sessions. For prescriptions, "
    "generic drugs cost $10."
)

faith = evaluate("faithfulness", output=faithful_but_wrong, context=wrong_chunks)
relevancy = evaluate("answer_relevancy", output=faithful_but_wrong, input=question)
precision = evaluate(
    "context_precision", output=faithful_but_wrong,
    context=wrong_chunks, input=question,
)

print(f"Retrieval:")
print(f"  Context precision: {precision.score:.2f}  (chunks are irrelevant!)")
print(f"\nGeneration:")
print(f"  Faithfulness:      {faith.score:.2f}  (faithful to wrong context)")
print(f"  Answer relevancy:  {relevancy.score:.2f}  (doesn't address the question)")

Retrieval:
  Context precision: 0.05  (chunks are irrelevant!)

Generation:
  Faithfulness:      0.85  (faithful to wrong context)
  Answer relevancy:  0.10  (doesn't address the question)

noisy_chunks = [
    "Gold Plan Coverage -- Physical Therapy: Covered for in-network providers. "
    "Copay: $30 per visit. Maximum 30 visits per calendar year.",

    "Company holiday schedule: New Year's Day, MLK Day, Presidents' Day...",

    "IT Department: To reset your password, visit portal.company.com/reset",

    "Out-of-Network Services: Physical therapy out-of-network requires prior "
    "authorization. Copay: $75 per visit.",
]

precision = evaluate(
    "context_precision", output=good_answer, context=noisy_chunks, input=question,
)
utilization = evaluate(
    "context_utilization", output=good_answer, context=noisy_chunks,
)
noise = evaluate(
    "noise_sensitivity", output=good_answer, context=noisy_chunks, input=question,
)

print(f"Context precision:   {precision.score:.2f}  (only ~50% relevant)")
print(f"Context utilization: {utilization.score:.2f}  (used what was relevant)")
print(f"Noise sensitivity:   {noise.score:.2f}  (affected by noise)")

batch = evaluate(
    ["faithfulness", "answer_relevancy", "groundedness", "context_utilization"],
    output=good_answer,
    context=good_chunks,
    input=question,
)

for r in batch:
    status = "PASS" if r.passed else "FAIL"
    print(f"{r.eval_name:<25} {r.score:.2f}  {status}")
print(f"\nOverall: {batch.success_rate:.0%} passed")