REP elicits hidden LLM reasoning traces via in-context shadow demonstrations, raising similarity to internal traces while retaining distillation utility across datasets and models.
How to Steal Reasoning Without Reasoning Traces
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Many large language models (LLMs) use reasoning to generate responses but do not reveal their full reasoning traces (a.k.a. chains of thought), instead outputting only final answers and brief reasoning summaries. To demonstrate that hiding reasoning traces does not prevent users from "stealing" a model's reasoning capabilities, we introduce trace inversion models that, given only the inputs, answers, and (optionally) reasoning summaries exposed by a target model, generate detailed, synthetic reasoning traces. We show that (1) traces synthesized by trace inversion have high overlap with the ground-truth reasoning traces (when available), and (2) fine-tuning student models on inverted traces substantially improves their reasoning and enables distillation from proprietary, black-box LLMs.
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Recon scores reasoning traces via action reconstruction fidelity, achieving 54.7% win rate over post-hoc baselines and up to 70% when used to train synthesis models across four domains.
citing papers explorer
-
Hidden Thoughts Are Not Secret: Reasoning Trace Exposure in LLMs
REP elicits hidden LLM reasoning traces via in-context shadow demonstrations, raising similarity to internal traces while retaining distillation utility across datasets and models.
-
Recon: Reconstruction-Guided Reasoning Synthesis for User Modeling
Recon scores reasoning traces via action reconstruction fidelity, achieving 54.7% win rate over post-hoc baselines and up to 70% when used to train synthesis models across four domains.