跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.20566 · v1

Weight-Space Programming Changes How an LLM Uses Python for Computational Biology

首次提交 2026-11-16 13:44
版本更新 2026-11-16 13:44
雷达观测 2026-11-17 13:07
arXiv ↗PDF ↗

摘要

Weight-space programming allows a language model to edit another model's weights without gradient-based training. We used Claude Opus 5.5 to edit Qwen3.5-0.8B and investigated how the edits changed its use of Python on computational biology problems. We compared four initial edited checkpoints with the original model on 50 test problems across three test seeds, yielding 600 paired evaluations. Strictly correct answers increased from 44 to 77, and technically correct answers, which included correct final values rejected for formatting, increased from 64 to 100. Repeated Python calls decreased from 1,834 to 1,044. Among the 64 pairs in which only the edited response was technically correct, the original model had already computed the correct value in 36 but did not submit a technically correct final answer. The edited model corrected the computation in 13 of the 64 pairs. With six additional checkpoints on the same 50 problems, technically correct answers rose from 96 to 154 across 900 pairs. We explored three selected problems with ten test seeds for each of ten checkpoints. On the melting-temperature problem, correct Python outputs decreased from 60 to 22 while technically correct final answers increased from 0 to 18. Weight editing changed both the calculations Qwen ran and whether it submitted a correct answer.

作者备注:16 pages, 3 figures, 6 main tables, and 1 supplementary table

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-16 13:44 · 最新观测版本

Weight-Space Programming Changes How an LLM Uses Python for Computational Biology

Weight-space programming allows a language model to edit another model's weights without gradient-based training. We used Claude Opus 5.5 to edit Qwen3.5-0.8B and investigated how the edits changed its use of Python on computational biology problems. We compared four initial edited checkpoints with the original model on 50 test problems across three test seeds, yielding 600 paired evaluations. Strictly correct answers increased from 44 to 77, and technically correct answers, which included correct final values rejected for formatting, increased from 64 to 100. Repeated Python calls decreased from 1,834 to 1,044. Among the 64 pairs in which only the edited response was technically correct, the original model had already computed the correct value in 36 but did not submit a technically correct final answer. The edited model corrected the computation in 13 of the 64 pairs. With six additional checkpoints on the same 50 problems, technically correct answers rose from 96 to 154 across 900 pairs. We explored three selected problems with ten test seeds for each of ten checkpoints. On the melting-temperature problem, correct Python outputs decreased from 60 to 22 while technically correct final answers increased from 0 to 18. Weight editing changed both the calculations Qwen ran and whether it submitted a correct answer.

查看此版本解读 →查看此版本原文 ↗