Knowledge Retention

The knowledge retention metric is a conversational metric that determines whether your LLM chatbot is able to retain factual information presented throughout a conversation.

Required Arguments

To use the KnowledgeRetentionMetric, you'll have to provide the following arguments when creating a ConversationalTestCase:

• turns

You must provide the role and content for evaluation to happen. Read the How Is It Calculated section below to learn more.

Usage

First, set the eval mode:

deepeval set-eval-mode llm         # LLM-as-a-judge (default)
deepeval set-eval-mode hybrid      # LLM extracts, Jev decides
deepeval set-eval-mode system_one  # Jev-as-a-judge, no LLM

The KnowledgeRetentionMetric() can be used for end-to-end multi-turn evaluation:

from deepeval.test_case import Turn, ConversationalTestCase
from deepeval.metrics import KnowledgeRetentionMetric
from deepeval import evaluate

convo_test_case = ConversationalTestCase(
    turns=[Turn(role="...", content="..."), Turn(role="...", content="...")]
)
metric = KnowledgeRetentionMetric(threshold=0.5)

# To run metric as a standalone
# metric.measure(convo_test_case)
# print(metric.score, metric.reason)

evaluate(test_cases=[convo_test_case], metrics=[metric])

There are EIGHT optional parameters when creating a KnowledgeRetentionMetric:

• [Optional] threshold: a number representing the minimum passing threshold. Can also be set to None to run the metric in score-only mode. Defaulted to 0.5.
• [Optional] model: a string specifying which of OpenAI's GPT models to use, OR any custom LLM model of type DeepEvalBaseLLM. Defaulted to gpt-5.4.
• [Optional] include_reason: a boolean which when set to True, will include a reason for its evaluation score. Defaulted to True.
• [Optional] strict_mode: a boolean which when set to True, enforces a binary metric score: 1 for perfection, 0 otherwise. It also overrides the current threshold and sets it to 0. Defaulted to False.
• [Optional] verbose_mode: a boolean which when set to True, prints the intermediate steps used to calculate said metric to the console, as outlined in the How Is It Calculated section. Defaulted to False.
• [Optional] flaky: a boolean which when set to True, marks the metric as flaky. Defaulted to False.
• [Optional] system_one_model: the Jev model to use, as a string or a DeepEvalBaseSystemOneModel. Only used under hybrid or system_one eval_mode. Defaulted to jev-latest.
• [Optional] eval_mode: llm, hybrid or system_one, choosing whether an LLM, Jev, or both judge. Defaulted to the configured eval mode (llm unless set).

As a standalone

You can also run the KnowledgeRetentionMetric on a single test case as a standalone, one-off execution.

...

metric.measure(test_case)
print(metric.score, metric.reason)

How Is It Calculated?

You can change how the KnowledgeRetentionMetric is calculated by setting the eval mode.

LLM-as-a-judge

The KnowledgeRetentionMetric score is calculated according to the following equation:

The KnowledgeRetentionMetric first uses an LLM to extract knowledge supplied in "content" by the "user" role throughout turns, before using the same LLM to determine whether each corresponding "assistant" content indicates an inability to recall said knowledge.

Hybrid

Under the hybrid eval mode, the LLM still extracts the knowledge from each user turn, but whether each assistant turn forgets or contradicts it is answered by Jev, a System One model: one yes/no question per assistant turn, with P(yes) >= 0.5 counted as a knowledge attrition. The equation and the LLM-written reason are unchanged. If a Jev call fails, the LLM makes that decision instead.

Jev-as-a-judge

Under the system_one eval mode, Jev judges the whole metric in one request. It is sent the whole conversation and asked three questions:

Each answer becomes a value in $[0, 1]$ and the score is their weighted mean. No LLM is called: the reason lists each answer with its probability, and metric.confidence reports how decisive Jev was.

FAQs