← 研踪 PaperTrailarXiv: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
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
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 ↗