I-D Action: draft-gaikwad-llm-fault-detection-terminology-00.txt

Internet-Draft draft-gaikwad-llm-fault-detection-terminology-00.txt is now
available.

   Title:   Benchmarking Terminology for Output Behavior Fault Detection in Large Language Model Serving Systems
   Author:  Madhava Gaikwad
   Name:    draft-gaikwad-llm-fault-detection-terminology-00.txt
   Pages:   14
   Dates:   2026-08-11

Abstract:

   This document defines terminology for benchmarking the fault
   detection capability of observability systems that monitor Large
   Language Model (LLM) serving deployments.  It defines terms for
   injectable output behavior fault classes, for the detection events
   and latency intervals those faults produce, and for the coverage and
   accuracy characteristics of the detector under test.

   The System Under Test is the observability system, and not the
   language model.  Faults are injected at a known time under controlled
   conditions, which makes detection latency measurable in a way it is
   not in production.

   This document defines terminology only.  A companion document defines
   the corresponding methodology.  This document specifies no test
   procedures, no acceptance thresholds, and no service-level
   objectives.

The IETF datatracker status page for this Internet-Draft is:
https://datatracker.ietf.org/doc/draft-gaikwad-llm-fault-detection-terminology/

There is also an HTML version available at:
https://www.ietf.org/archive/id/draft-gaikwad-llm-fault-detection-terminology-00.html

Internet-Drafts are also available by rsync at:
rsync.ietf.org::internet-drafts


_______________________________________________
I-D-Announce mailing list -- [email protected]
To unsubscribe send an email to [email protected]