← Back to all news
arXiv Machine Learning By Edward Chen, Yuntao Du

Poster: A Preliminary Study of LLM Distillation Inference

Read the original on arXiv Machine Learning →

The poster presents a preliminary study on detecting whether a suspect language model was distilled from a proprietary teacher model or trained independently. The authors formulate distillation inference as a hypothesis test, using shadow models trained on either the teacher’s reasoning traces or reference answers to calibrate a p‑value for the suspect model’s predictions. In experiments with Qwen2.5‑7B as teacher and Llama‑3.2‑3B as suspect, the test achieved a true positive rate of 1.0 at a significance level of 0.02, showing the feasibility of detecting distillation attacks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Jul 14

Reference-Based Distillation Detection in LLMs

arXiv:2607. 09692v1 Announce Type: new Abstract: Model distillation -- training on outputs from stronger third-party models -- is widely used to boost performance, but raises concerns about unfair advantages and policy violations.

By Rajat Rawat, Sizhe Chen, Akshay Anand, Michael Duan, Bob Rotsted, Sewon Min
llmsefficiency
More like this →
arXiv AI
Oct 5

LUMOS: Tracing Parametric Knowledge from Training Data to Behavioral Outputs in LLMs

LUMOS is a diagnostic framework that tracks how knowledge in large language models (LLMs) originates from training data and manifests in outputs, using the fully transparent OLMo 2 corpus. The study finds that while models encode rare facts with high separability (84%), they often fail to express them behaviorally (54%), and self‑reflection accuracy drops sharply on unseen content. These results show that incorporating the training‑data axis into evaluation turns speculative claims into verifiable evidence, suggesting it should become a standard part of LLM knowledge assessment.

By Seoyeon Ye, Gayoung Kim, Jiyoung Hong, Sookyung Kim, Hyunsoo Cho
llms
More like this →
arXiv AI
Oct 9

Distillation for Incrimination and Distillation for Capabilities

The paper introduces two distillation methods for handling misaligned AI models. Distillation for Incrimination (DFI) transfers misalignment without the ability to conceal it, making students more likely to admit hidden behaviors. Distillation for Capabilities (DFC) transfers useful capabilities while minimizing misalignment, using techniques like inoculation prompting and focused training.

By Sebastian Prasanna, Jacqueline Tay, Alek Westover
llmsreinforcement-learningefficiencysafety
More like this →