按年被提到
20262026 · 3 次2026
大模型与语言模型›大模型推理与思维链·arXiv:2603.07267 · cs.CR

How to Steal Reasoning Without Reasoning Traces

Tingwei Zhang, John X. Morris, Vitaly Shmatikov · 2026
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 3 人首次 2026-06-17 · 最近 2026-08-18
3不同的人
2活跃月份
3讨论串
1被引(OpenAlex)
arXiv 摘要(候选层不写导读)

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.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论nyrikki · 2026-06

“It is quite likely that the intermediate tokens don’t have ‘semantic import’[0] There are methods like Habitual Reasoning Distillation or Inverted Reasoning Traces [1] that can help. While there are reasons to hide the intermediate tokens from a IP protection stand point, there is also a need to hide more effective and efficient generating that doesn’t …”

GLM-5.2 is the new leading open weights model on Artificial Analysis原评论 ↗
评论nervai · 2026-08

“Really cool work, you get the actual traces. Looks like the vendors can all reliably fix this one though. A harder to defend against approach here where they work backwards from the results and ask the model to generate a plausible trace: How to Steal Reasoning Without Reasoning Traces https://arxiv.org/pdf/2603.07267”

Stealing Reasoning Traces from Proprietary LLM APIs原评论 ↗
评论dannyw · 2026-08

“You can train a LLM to inverse summarised thinking into thinking text. It’s not perfect, but it gets you maybe 80% of the quality with proper techniques. Paper: https://arxiv.org/abs/2603.07267 FWIW, there’s not that much value protected here anyway IMHO, and even raw thinking text can lie (as shown by Anthropic’s amazing research), so for legitimate in…”

GPT-5.6 Sol Pricing Cut by 50%原评论 ↗