conftrace_

training data tracing

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

verbatim match (1) corpus retrieval (1) adversarial query (1) fact checking (1) training data (1) membership inference (1) hallucination detection (1) language model (1) text retrieval (1) false positive rate (1)

Papers

OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens ACL 2025 Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries ICLR 2023